Showing 1–50 of 97 results for author: Talwalkar, A

Comparing Developer and LLM Biases in Code Evaluation

Authors: Aditya Mittal, Ryan Shar, Zichu Wu, Shyam Agarwal, Tongshuang Wu, Chris Donahue, Ameet Talwalkar, Wayne Chi, Valerie Chen

Abstract: As LLMs are increasingly used as judges in code applications, they should be evaluated in realistic interactive settings that capture partial context and ambiguous intent. We present TRACE (Tool for Rubric Analysis in Code Evaluation), a framework that evaluates LLM judges' ability to predict human preferences and automatically extracts rubric items to reveal systematic biases in how humans and mo… ▽ More As LLMs are increasingly used as judges in code applications, they should be evaluated in realistic interactive settings that capture partial context and ambiguous intent. We present TRACE (Tool for Rubric Analysis in Code Evaluation), a framework that evaluates LLM judges' ability to predict human preferences and automatically extracts rubric items to reveal systematic biases in how humans and models weigh each item. Across three modalities -- chat-based programming, IDE autocompletion, and instructed code editing -- we use TRACE to measure how well LLM judges align with developer preferences. Among 13 different models, the best judges underperform human annotators by 12-23%. TRACE identifies 35 significant sources of misalignment between humans and judges across interaction modalities, the majority of which correspond to existing software engineering code quality criteria. For example, in chat-based coding, judges are biased towards longer code explanations while humans prefer shorter ones. We find significant misalignment on the majority of existing code quality dimensions, showing alignment gaps between LLM judges and human preference in realistic coding applications. △ Less

Submitted 25 March, 2026; originally announced March 2026.

Learn Hard Problems During RL with Reference Guided Fine-tuning

Authors: Yangzhen Wu, Shanda Li, Zixin Wen, Xin Zhou, Ameet Talwalkar, Yiming Yang, Wenhao Huang, Tianle Cai

Abstract: Reinforcement learning (RL) for mathematical reasoning can suffer from reward sparsity: for challenging problems, LLM fails to sample any correct trajectories, preventing RL from receiving meaningful positive feedback. At the same time, there often exist human-written reference solutions along with the problem (e.g., problems from AoPS), but directly fine-tuning on these solutions offers no benefi… ▽ More Reinforcement learning (RL) for mathematical reasoning can suffer from reward sparsity: for challenging problems, LLM fails to sample any correct trajectories, preventing RL from receiving meaningful positive feedback. At the same time, there often exist human-written reference solutions along with the problem (e.g., problems from AoPS), but directly fine-tuning on these solutions offers no benefit because models often cannot imitate human proofs that lie outside their own reasoning distribution. We introduce Reference-Guided Fine-Tuning (ReGFT), a simple and effective method that utilizes human-written reference solutions to synthesize positive trajectories on hard problems and train on them before RL. For each problem, we provide the model with a partial reference solution and let it generate its own reasoning trace, ensuring the resulting trajectories remain in the model's reasoning space while still benefiting from reference guidance. Fine-tuning on these reference-guided trajectories increases the number of solvable problems and produces a checkpoint that receives more positive rewards during RL. Across three benchmarks (AIME24, AIME25, BeyondAIME), ReGFT consistently improves supervised accuracy, accelerates DAPO training, and raises the final performance plateau of RL. Our results show that ReGFT effectively overcomes reward sparsity and unlocks stronger RL-based mathematical reasoning. △ Less

Submitted 5 March, 2026; v1 submitted 1 March, 2026; originally announced March 2026.

Comments: 15 pages, 5 figures

GameDevBench: Evaluating Agentic Capabilities Through Game Development

Authors: Wayne Chi, Yixiong Fang, Arnav Yayavaram, Siddharth Yayavaram, Seth Karten, Qiuhong Anna Wei, Runkun Chen, Alexander Wang, Valerie Chen, Ameet Talwalkar, Chris Donahue

Abstract: Despite rapid progress on coding agents, progress on their multimodal counterparts has lagged behind. A key challenge is the scarcity of evaluation testbeds that combine the complexity of software development with the need for deep multimodal understanding. Game development provides such a testbed as agents must navigate large, dense codebases while manipulating intrinsically multimodal assets suc… ▽ More Despite rapid progress on coding agents, progress on their multimodal counterparts has lagged behind. A key challenge is the scarcity of evaluation testbeds that combine the complexity of software development with the need for deep multimodal understanding. Game development provides such a testbed as agents must navigate large, dense codebases while manipulating intrinsically multimodal assets such as shaders, sprites, and animations within a visual game scene. We present GameDevBench, the first benchmark for evaluating agents on game development tasks. GameDevBench consists of 132 tasks derived from web and video tutorials. Tasks require significant multimodal understanding and are complex -- the average solution requires over three times the amount of lines of code and file changes compared to prior software development benchmarks. Agents still struggle with game development, with the best agent solving only 54.5% of tasks. We find a strong correlation between perceived task difficulty and multimodal complexity, with success rates dropping from 46.9% on gameplay-oriented tasks to 31.6% on 2D graphics tasks. To improve multimodal capability, we introduce two simple image and video-based feedback mechanisms for agents. Despite their simplicity, these methods consistently improve performance, with the largest change being an increase in Claude Sonnet 4.5's performance from 33.3% to 47.7%. We release GameDevBench publicly to support further research into agentic game development. △ Less

Submitted 11 February, 2026; originally announced February 2026.

Beyond the Commit: Developer Perspectives on Productivity with AI Coding Assistants

Authors: Valerie Chen, Jasmyn He, Behnjamin Williams, Jason Valentino, Ameet Talwalkar

Abstract: Measuring developer productivity is a topic that has attracted attention from both academic research and industrial practice. In the age of AI coding assistants, it has become even more important for both academia and industry to understand how to measure their impact on developer productivity, and to reconsider whether earlier measures and frameworks still apply. This study analyzes the validity… ▽ More Measuring developer productivity is a topic that has attracted attention from both academic research and industrial practice. In the age of AI coding assistants, it has become even more important for both academia and industry to understand how to measure their impact on developer productivity, and to reconsider whether earlier measures and frameworks still apply. This study analyzes the validity of different approaches to evaluating the productivity impacts of AI coding assistants by leveraging mixed-method research. At BNY Mellon, we conduct a survey with 2989 developer responses and 11 in-depth interviews. Our findings demonstrate that a multifaceted approach is needed to measure AI productivity impacts: survey results expose conflicting perspectives on AI tool usefulness, while interviews elicit six distinct factors that capture both short-term and long-term dimensions of productivity. In contrast to prior work, our factors highlight the importance of long-term metrics like technical expertise and ownership of work. We hope this work encourages future research to incorporate a broader range of human-centered factors, and supports industry in adopting more holistic approaches to evaluating developer productivity. △ Less

Submitted 3 February, 2026; originally announced February 2026.

Comments: ICSE SEIP

Pre-Generating Multi-Difficulty PDE Data for Few-Shot Neural PDE Solvers

Authors: Naman Choudhary, Vedant Singh, Ameet Talwalkar, Nicholas Matthew Boffi, Mikhail Khodak, Tanya Marwah

Abstract: A key aspect of learned partial differential equation (PDE) solvers is that the main cost often comes from generating training data with classical solvers rather than learning the model itself. Another is that there are clear axes of difficulty--e.g., more complex geometries and higher Reynolds numbers--along which problems become (1) harder for classical solvers and thus (2) more likely to benefi… ▽ More A key aspect of learned partial differential equation (PDE) solvers is that the main cost often comes from generating training data with classical solvers rather than learning the model itself. Another is that there are clear axes of difficulty--e.g., more complex geometries and higher Reynolds numbers--along which problems become (1) harder for classical solvers and thus (2) more likely to benefit from neural speedups. Towards addressing this chicken-and-egg challenge, we study difficulty transfer on 2D incompressible Navier-Stokes, systematically varying task complexity along geometry (number and placement of obstacles), physics (Reynolds number), and their combination. Similar to how it is possible to spend compute to pre-train foundation models and improve their performance on downstream tasks, we find that by classically solving (analogously pre-generating) many low and medium difficulty examples and including them in the training set, it is possible to learn high-difficulty physics from far fewer samples. Furthermore, we show that by combining low and high difficulty data, we can spend 8.9x less compute on pre-generating a dataset to achieve the same error as using only high difficulty examples. Our results highlight that how we allocate classical-solver compute across difficulty levels is as important as how much we allocate overall, and suggest substantial gains from principled curation of pre-generated PDE data for neural solvers. Our code is available at https://github.com/Naman-Choudhary-AI-ML/pregenerating-pde △ Less

Submitted 22 January, 2026; v1 submitted 29 November, 2025; originally announced December 2025.

Comments: 10 Pages, 11 Figures

EDIT-Bench: Evaluating LLM Abilities to Perform Real-World Instructed Code Edits

Authors: Wayne Chi, Valerie Chen, Ryan Shar, Aditya Mittal, Jenny Liang, Wei-Lin Chiang, Anastasios Nikolas Angelopoulos, Ion Stoica, Graham Neubig, Ameet Talwalkar, Chris Donahue

Abstract: Instructed code editing, where LLMs directly modify a developer's existing code based on a user instruction, is becoming a widely used interaction mode in AI coding assistants. However, few benchmarks directly evaluate this capability and current datasets often rely on artificial sources. We introduce EDIT-Bench, a benchmark for evaluating LLM code editing capabilities grounded in real-world usage… ▽ More Instructed code editing, where LLMs directly modify a developer's existing code based on a user instruction, is becoming a widely used interaction mode in AI coding assistants. However, few benchmarks directly evaluate this capability and current datasets often rely on artificial sources. We introduce EDIT-Bench, a benchmark for evaluating LLM code editing capabilities grounded in real-world usage, i.e., user instructions and code contexts collected in the wild. EDIT-Bench comprises of 540 problems, multiple natural and programming languages, and a diverse set of real-world use cases, ranging from resolving errors to adding features. EDIT-Bench introduces context-dependent problems that require the model to understand code context, highlighted code, and cursor position in addition to the user instruction. We evaluate 40 diverse LLMs and observe that EDIT-Bench is a challenging set of problems where only 1 model scores over 60%. We find that model performance varies across different categories of user instructions. Further, we find that varying levels of contextual information greatly affect task success rate, with performance varying up to 11%, indicating the importance of evaluating with realistic context. △ Less

Submitted 17 November, 2025; v1 submitted 6 November, 2025; originally announced November 2025.

Completion $\neq$ Collaboration: Scaling Collaborative Effort with Agents

Authors: Shannon Zejiang Shen, Valerie Chen, Ken Gu, Alexis Ross, Zixian Ma, Jillian Ross, Alex Gu, Chenglei Si, Wayne Chi, Andi Peng, Jocelyn J Shen, Ameet Talwalkar, Tongshuang Wu, David Sontag

Abstract: Current evaluations of agents remain centered around one-shot task completion, failing to account for the inherently iterative and collaborative nature of many real-world problems, where human goals are often underspecified and evolve. We argue for a shift from building and assessing task completion agents to developing collaborative agents, assessed not only by the quality of their final outputs… ▽ More Current evaluations of agents remain centered around one-shot task completion, failing to account for the inherently iterative and collaborative nature of many real-world problems, where human goals are often underspecified and evolve. We argue for a shift from building and assessing task completion agents to developing collaborative agents, assessed not only by the quality of their final outputs but by how well they engage with and enhance human effort throughout the problem-solving process. To support this shift, we introduce collaborative effort scaling, a framework that captures how an agent's utility grows with increasing user involvement. Through case studies and simulated evaluations, we show that state-of-the-art agents often underperform in multi-turn, real-world scenarios, revealing a missing ingredient in agent design: the ability to sustain engagement and scaffold user understanding. Collaborative effort scaling offers a lens for diagnosing agent behavior and guiding development toward more effective interactions. △ Less

Submitted 30 October, 2025; v1 submitted 29 October, 2025; originally announced October 2025.

Comments: 22 pages, 5 figures, 3 tables

RECODE: Reasoning Through Code Generation for Visual Question Answering

Authors: Junhong Shen, Mu Cai, Bo Hu, Ameet Talwalkar, David A Ross, Cordelia Schmid, Alireza Fathi

Abstract: Multimodal Large Language Models (MLLMs) struggle with precise reasoning for structured visuals like charts and diagrams, as pixel-based perception lacks a mechanism for verification. To address this, we propose to leverage derendering -- the process of reverse-engineering visuals into executable code -- as a new modality for verifiable visual reasoning. Specifically, we propose RECODE, an agentic… ▽ More Multimodal Large Language Models (MLLMs) struggle with precise reasoning for structured visuals like charts and diagrams, as pixel-based perception lacks a mechanism for verification. To address this, we propose to leverage derendering -- the process of reverse-engineering visuals into executable code -- as a new modality for verifiable visual reasoning. Specifically, we propose RECODE, an agentic framework that first generates multiple candidate programs to reproduce the input image. It then uses a critic to select the most faithful reconstruction and iteratively refines the code. This process not only transforms an ambiguous perceptual task into a verifiable, symbolic problem, but also enables precise calculations and logical inferences later on. On various visual reasoning benchmarks such as CharXiv, ChartQA, and Geometry3K, RECODE significantly outperforms methods that do not leverage code or only use code for drawing auxiliary lines or cropping. Our work demonstrates that grounding visual perception in executable code provides a new path toward more accurate and verifiable multimodal reasoning. △ Less

Submitted 10 March, 2026; v1 submitted 15 October, 2025; originally announced October 2025.

Comments: The authors are withdrawing this manuscript temporarily to conduct additional checks of the experimental setup and implementation. We plan to post an updated version after completing these checks

How can we assess human-agent interactions? Case studies in software agent design

Authors: Valerie Chen, Rohit Malhotra, Xingyao Wang, Juan Michelini, Xuhui Zhou, Aditya Bharat Soni, Hoang H. Tran, Calvin Smith, Ameet Talwalkar, Graham Neubig

Abstract: LLM-powered agents are both a promising new technology and a source of complexity, where choices about models, tools, and prompting can affect their usefulness. While numerous benchmarks measure agent accuracy across domains, they mostly assume full automation, failing to represent the collaborative nature of real-world use cases. In this paper, we make two major steps towards the rigorous assessm… ▽ More LLM-powered agents are both a promising new technology and a source of complexity, where choices about models, tools, and prompting can affect their usefulness. While numerous benchmarks measure agent accuracy across domains, they mostly assume full automation, failing to represent the collaborative nature of real-world use cases. In this paper, we make two major steps towards the rigorous assessment of human-agent interactions. First, we propose PULSE, a framework for more efficient human-centric evaluation of agent designs, which comprises collecting user feedback, training an ML model to predict user satisfaction, and computing results by combining human satisfaction ratings with model-generated pseudo-labels. Second, we deploy the framework on a large-scale web platform built around the open-source software agent OpenHands, collecting in-the-wild usage data across over 15k users. We conduct case studies around how three agent design decisions -- choice of LLM backbone, planning strategy, and memory mechanisms -- impact developer satisfaction rates, yielding practical insights for software agent design. We also show how our framework can lead to more robust conclusions about agent design, reducing confidence intervals by 40% compared to a standard A/B test. Finally, we find substantial discrepancies between in-the-wild results and benchmark performance (e.g., the anti-correlation between results comparing claude-sonnet-4 and gpt-5), underscoring the limitations of benchmark-driven evaluation. Our findings provide guidance for evaluations of LLM agents with humans and identify opportunities for better agent designs. △ Less

Submitted 4 November, 2025; v1 submitted 10 October, 2025; originally announced October 2025.

Why Do Decision Makers (Not) Use AI? A Cross-Domain Analysis of Factors Impacting AI Adoption

Authors: Rebecca Yu, Valerie Chen, Ameet Talwalkar, Hoda Heidari

Abstract: Growing excitement around deploying AI across various domains calls for a careful assessment of how human decision-makers interact with AI-powered systems. In particular, it is essential to understand when decision-makers voluntarily choose to consult AI tools, which we term decision-maker adoption. We interviewed experts across four domains -- medicine, law, journalism, and the public sector -- t… ▽ More Growing excitement around deploying AI across various domains calls for a careful assessment of how human decision-makers interact with AI-powered systems. In particular, it is essential to understand when decision-makers voluntarily choose to consult AI tools, which we term decision-maker adoption. We interviewed experts across four domains -- medicine, law, journalism, and the public sector -- to explore current AI use cases and perceptions of adoption. From these interviews, we identify key factors that shape decision-maker adoption of AI tools: the decision-maker's background, perceptions of the AI, consequences for the decision-maker, and perceived implications for other stakeholders. We translate these factors into an AI adoption sheet to analyze how decision-makers approach adoption choices through comparative, cross-domain case studies, highlighting how our factors help explain inter-domain differences in adoption. Our findings offer practical guidance for supporting the responsible and context-aware deployment of AI by better accounting for the decision-maker's perspective. △ Less

Submitted 1 August, 2025; originally announced August 2025.

Comments: To be published in Proceedings of the Eighth AAAI/ACM Conference on AI, Ethics, and Society (AIES-25). 10 pages, 4 figures, 1 table

Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows

Authors: Valerie Chen, Ameet Talwalkar, Robert Brennan, Graham Neubig

Abstract: Developers now have access to a growing array of increasingly autonomous AI tools for software development. While many studies examine copilots that provide chat assistance or code completions, evaluations of coding agents -- which can automatically write files and run code -- still rely on static benchmarks. We present the first controlled study of developer interactions with coding agents, chara… ▽ More Developers now have access to a growing array of increasingly autonomous AI tools for software development. While many studies examine copilots that provide chat assistance or code completions, evaluations of coding agents -- which can automatically write files and run code -- still rely on static benchmarks. We present the first controlled study of developer interactions with coding agents, characterizing how more autonomous AI tools affect productivity and experience. We evaluate two leading copilot and agentic coding assistants, recruiting participants who regularly use the former. Our results show agents can assist developers in ways that surpass copilots (e.g., completing tasks humans may not have accomplished) and reduce the effort required to finish tasks. Yet challenges remain for broader adoption, including ensuring users adequately understand agent behaviors. Our findings reveal how workflows shift with coding agents and how interactions differ from copilots, motivating recommendations for researchers and highlighting challenges in adopting agentic systems. △ Less

Submitted 13 September, 2025; v1 submitted 10 July, 2025; originally announced July 2025.

CoMind: Towards Community-Driven Agents for Machine Learning Engineering

Authors: Sijie Li, Weiwei Sun, Shanda Li, Ameet Talwalkar, Yiming Yang

Abstract: Large language model (LLM) agents show promise in automating machine learning (ML) engineering. However, existing agents typically operate in isolation on a given research problem, without engaging with the broader research community, where human researchers often gain insights and contribute by sharing knowledge. To bridge this gap, we introduce MLE-Live, a live evaluation framework designed to a… ▽ More Large language model (LLM) agents show promise in automating machine learning (ML) engineering. However, existing agents typically operate in isolation on a given research problem, without engaging with the broader research community, where human researchers often gain insights and contribute by sharing knowledge. To bridge this gap, we introduce MLE-Live, a live evaluation framework designed to assess an agent's ability to communicate with and leverage collective knowledge from a simulated Kaggle research community. Building on this framework, we propose CoMind, a multi-agent system designed to systematically leverage external knowledge. CoMind employs an iterative parallel exploration mechanism, developing multiple solutions simultaneously to balance exploratory breadth with implementation depth. On 75 past Kaggle competitions within our MLE-Live framework, CoMind achieves a 36% medal rate, establishing a new state of the art. Critically, when deployed in eight live, ongoing competitions, CoMind outperforms 92.6% of human competitors on average, placing in the top 5% on three official leaderboards and the top 1% on one. △ Less

Submitted 27 February, 2026; v1 submitted 25 June, 2025; originally announced June 2025.

Comments: ICLR 2026. Code available at https://github.com/comind-ml/CoMind

Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction

Authors: Junhong Shen, Hao Bai, Lunjun Zhang, Yifei Zhou, Amrith Setlur, Shengbang Tong, Diego Caples, Nan Jiang, Tong Zhang, Ameet Talwalkar, Aviral Kumar

Abstract: The current paradigm of test-time scaling relies on generating long reasoning traces ("thinking" more) before producing a response. In agent problems that require interaction, this can be done by generating thinking traces before acting in the world. However, this process does not allow agents to acquire new information from the environment or adapt their behavior over time. In this work, we propo… ▽ More The current paradigm of test-time scaling relies on generating long reasoning traces ("thinking" more) before producing a response. In agent problems that require interaction, this can be done by generating thinking traces before acting in the world. However, this process does not allow agents to acquire new information from the environment or adapt their behavior over time. In this work, we propose to scale test-time interaction, an untapped dimension of test-time scaling that increases the agent's interaction horizon to enable running rich behaviors such as exploration, backtracking, and dynamic re-planning within a single rollout. To demonstrate the promise of this scaling dimension, we study the domain of web agents. We first show that even prompting-based interaction scaling without any training can improve task success on web benchmarks non-trivially. Building on this, we introduce TTI (Test-Time Interaction), a curriculum-based online reinforcement learning (RL) approach that trains agents by adaptively adjusting their rollout lengths. Using a Gemma 3 12B model, TTI produces state-of-the-art open-source, open-data web agents on WebVoyager and WebArena benchmarks. We further show that TTI enables agents to balance exploration and exploitation adaptively. Our results establish interaction scaling as a powerful, complementary axis to scaling per-step compute, offering new avenues for training adaptive agents. △ Less

Submitted 10 June, 2025; v1 submitted 9 June, 2025; originally announced June 2025.

Comments: Fixed typo in Figure 6 and Conclusion

Sample Complexity and Representation Ability of Test-time Scaling Paradigms

Authors: Baihe Huang, Shanda Li, Tianhao Wu, Yiming Yang, Ameet Talwalkar, Kannan Ramchandran, Michael I. Jordan, Jiantao Jiao

Abstract: Test-time scaling paradigms have significantly advanced the capabilities of large language models (LLMs) on complex tasks. Despite their empirical success, theoretical understanding of the sample efficiency of various test-time strategies -- such as self-consistency, best-of-$n$, and self-correction -- remains limited. In this work, we first establish a separation result between two repeated sampl… ▽ More Test-time scaling paradigms have significantly advanced the capabilities of large language models (LLMs) on complex tasks. Despite their empirical success, theoretical understanding of the sample efficiency of various test-time strategies -- such as self-consistency, best-of-$n$, and self-correction -- remains limited. In this work, we first establish a separation result between two repeated sampling strategies: self-consistency requires $Θ(1/Δ^2)$ samples to produce the correct answer, while best-of-$n$ only needs $Θ(1/Δ)$, where $Δ< 1$ denotes the probability gap between the correct and second most likely answers. Next, we present an expressiveness result for the self-correction approach with verifier feedback: it enables Transformers to simulate online learning over a pool of experts at test time. Therefore, a single Transformer architecture can provably solve multiple tasks without prior knowledge of the specific task associated with a user query, extending the representation theory of Transformers from single-task to multi-task settings. Finally, we empirically validate our theoretical results, demonstrating the practical effectiveness of self-correction methods. △ Less

Submitted 12 June, 2025; v1 submitted 5 June, 2025; originally announced June 2025.

FrontierCO: Real-World and Large-Scale Evaluation of Machine Learning Solvers for Combinatorial Optimization

Authors: Shengyu Feng, Weiwei Sun, Shanda Li, Ameet Talwalkar, Yiming Yang

Abstract: Machine learning (ML) has shown promise for tackling combinatorial optimization (CO), but much of the reported progress relies on small-scale, synthetic benchmarks that fail to capture real-world structure and scale. A core limitation is that ML methods are typically trained and evaluated on synthetic instance generators, leaving open how they perform on irregular, competition-grade, or industrial… ▽ More Machine learning (ML) has shown promise for tackling combinatorial optimization (CO), but much of the reported progress relies on small-scale, synthetic benchmarks that fail to capture real-world structure and scale. A core limitation is that ML methods are typically trained and evaluated on synthetic instance generators, leaving open how they perform on irregular, competition-grade, or industrial datasets. We present FrontierCO, a benchmark for evaluating ML-based CO solvers under real-world structure and extreme scale. FrontierCO spans eight CO problems, including routing, scheduling, facility location, and graph problems, with instances drawn from competitions and public repositories (e.g., DIMACS, TSPLib). Each task provides both easy sets (historically challenging but now solvable) and hard sets (open or computationally intensive), alongside standardized training/validation resources. Using FrontierCO, we evaluate 16 representative ML solvers--graph neural approaches, hybrid neural-symbolic methods, and LLM-based agents--against state-of-the-art classical solvers. We find a persistent performance gap that widens under structurally challenging and large instance sizes (e.g., TSP up to 10M nodes; MIS up to 8M), while also identifying cases where ML methods outperform classical solvers. By centering evaluation on real-world structure and orders-of-magnitude larger instances, FrontierCO provides a rigorous basis for advancing ML for CO. Our benchmark is available at https://huggingface.co/datasets/CO-Bench/FrontierCO. △ Less

Submitted 9 March, 2026; v1 submitted 22 May, 2025; originally announced May 2025.

Comments: ICLR 2026

This Time is Different: An Observability Perspective on Time Series Foundation Models

Authors: Ben Cohen, Emaad Khwaja, Youssef Doubli, Salahidine Lemaachi, Chris Lettieri, Charles Masson, Hugo Miccinilli, Elise Ramé, Qiqi Ren, Afshin Rostamizadeh, Jean Ogier du Terrail, Anna-Monica Toon, Kan Wang, Stephan Xie, Zongzhe Xu, Viktoriya Zhukova, David Asker, Ameet Talwalkar, Othmane Abou-Amal

Abstract: We introduce Toto, a time series forecasting foundation model with 151 million parameters. Toto uses a modern decoder-only architecture coupled with architectural innovations designed to account for specific challenges found in multivariate observability time series data. Toto's pre-training corpus is a mixture of observability data, open datasets, and synthetic data, and is 4-10$\times$ larger th… ▽ More We introduce Toto, a time series forecasting foundation model with 151 million parameters. Toto uses a modern decoder-only architecture coupled with architectural innovations designed to account for specific challenges found in multivariate observability time series data. Toto's pre-training corpus is a mixture of observability data, open datasets, and synthetic data, and is 4-10$\times$ larger than those of leading time series foundation models. Additionally, we introduce BOOM, a large-scale benchmark consisting of 350 million observations across 2,807 real-world time series. For both Toto and BOOM, we source observability data exclusively from Datadog's own telemetry and internal observability metrics. Extensive evaluations demonstrate that Toto achieves state-of-the-art performance on both BOOM and on established general purpose time series forecasting benchmarks. Toto's model weights, inference code, and evaluation scripts, as well as BOOM's data and evaluation code, are all available as open source under the Apache 2.0 License available at https://huggingface.co/Datadog/Toto-Open-Base-1.0 and https://github.com/DataDog/toto. △ Less

Submitted 4 November, 2025; v1 submitted 20 May, 2025; originally announced May 2025.

CodePDE: An Inference Framework for LLM-driven PDE Solver Generation

Authors: Shanda Li, Tanya Marwah, Junhong Shen, Weiwei Sun, Andrej Risteski, Yiming Yang, Ameet Talwalkar

Abstract: Partial differential equations (PDEs) are fundamental to modeling physical systems, yet solving them remains a complex challenge. Traditional numerical solvers rely on expert knowledge to implement and are computationally expensive, while neural-network-based solvers require large training datasets and often lack interpretability. In this work, we frame PDE solving as a code generation task and in… ▽ More Partial differential equations (PDEs) are fundamental to modeling physical systems, yet solving them remains a complex challenge. Traditional numerical solvers rely on expert knowledge to implement and are computationally expensive, while neural-network-based solvers require large training datasets and often lack interpretability. In this work, we frame PDE solving as a code generation task and introduce CodePDE, the first inference framework for generating PDE solvers using large language models (LLMs). With CodePDE, we present a thorough evaluation on critical capacities of LLM for PDE solving: reasoning, debugging, self-refinement, and test-time scaling. CodePDE shows that, with advanced inference-time algorithms and scaling strategies, LLMs can achieve strong performance across a range of representative PDE problems. We also identify novel insights into LLM-driven solver generation, such as trade-offs between solver reliability and sophistication, design principles for LLM-powered PDE solving agents, and failure modes for LLM on hard tasks. These insights offer guidance for building more capable and reliable LLM-based scientific engines. △ Less

Submitted 22 February, 2026; v1 submitted 13 May, 2025; originally announced May 2025.

Comments: TMLR. Code available at https://github.com/LithiumDA/CodePDE

CodingGenie: A Proactive LLM-Powered Programming Assistant

Authors: Sebastian Zhao, Alan Zhu, Hussein Mozannar, David Sontag, Ameet Talwalkar, Valerie Chen

Abstract: While developers increasingly adopt tools powered by large language models (LLMs) in day-to-day workflows, these tools still require explicit user invocation. To seamlessly integrate LLM capabilities to a developer's workflow, we introduce CodingGenie, a proactive assistant integrated into the code editor. CodingGenie autonomously provides suggestions, ranging from bug fixing to unit testing, base… ▽ More While developers increasingly adopt tools powered by large language models (LLMs) in day-to-day workflows, these tools still require explicit user invocation. To seamlessly integrate LLM capabilities to a developer's workflow, we introduce CodingGenie, a proactive assistant integrated into the code editor. CodingGenie autonomously provides suggestions, ranging from bug fixing to unit testing, based on the current code context and allows users to customize suggestions by providing a task description and selecting what suggestions are shown. We demonstrate multiple use cases to show how proactive suggestions from CodingGenie can improve developer experience, and also analyze the cost of adding proactivity. We believe this open-source tool will enable further research into proactive assistants. CodingGenie is open-sourced at https://github.com/sebzhao/CodingGenie/ and video demos are available at https://sebzhao.github.io/CodingGenie/. △ Less

Submitted 18 March, 2025; originally announced March 2025.

Comments: FSE Demo 2025

When Benchmarks Talk: Re-Evaluating Code LLMs with Interactive Feedback

Authors: Jane Pan, Ryan Shar, Jacob Pfau, Ameet Talwalkar, He He, Valerie Chen

Abstract: Programming is a fundamentally interactive process, yet coding assistants are often evaluated using static benchmarks that fail to measure how well models collaborate with users. We introduce an interactive evaluation pipeline to examine how LLMs incorporate different types of feedback in a collaborative setting. Specifically, we perturb static coding benchmarks so that the code model must interac… ▽ More Programming is a fundamentally interactive process, yet coding assistants are often evaluated using static benchmarks that fail to measure how well models collaborate with users. We introduce an interactive evaluation pipeline to examine how LLMs incorporate different types of feedback in a collaborative setting. Specifically, we perturb static coding benchmarks so that the code model must interact with a simulated user to retrieve key information about the problem. We find that interaction significantly affects model performance, as the relative rankings of 10 models across 3 datasets often vary between static and interactive settings, despite models being fairly robust to feedback that contains errors. We also observe that even when different feedback types are equally effective with respect to performance, they can impact model behaviors such as (1) how models respond to higher- vs. lower-quality feedback and (2) whether models prioritize aesthetic vs. functional edits. Our work aims to "re-evaluate" model coding capabilities through an interactive lens toward bridging the gap between existing evaluations and real-world usage. △ Less

Submitted 25 February, 2025; originally announced February 2025.

Copilot Arena: A Platform for Code LLM Evaluation in the Wild

Authors: Wayne Chi, Valerie Chen, Anastasios Nikolas Angelopoulos, Wei-Lin Chiang, Aditya Mittal, Naman Jain, Tianjun Zhang, Ion Stoica, Chris Donahue, Ameet Talwalkar

Abstract: Evaluating in-the-wild coding capabilities of large language models (LLMs) is a challenging endeavor with no clear solution. We introduce Copilot Arena, a platform to collect user preferences for code generation through native integration into a developer's working environment. Copilot Arena comprises a novel interface for comparing pairs of model outputs, a sampling strategy optimized to reduce l… ▽ More Evaluating in-the-wild coding capabilities of large language models (LLMs) is a challenging endeavor with no clear solution. We introduce Copilot Arena, a platform to collect user preferences for code generation through native integration into a developer's working environment. Copilot Arena comprises a novel interface for comparing pairs of model outputs, a sampling strategy optimized to reduce latency, and a prompting scheme to enable code completion functionality. Copilot Arena has served over 4.5 million suggestions from 10 models and collected over 11k pairwise judgements. Our results highlight the importance of model evaluations in integrated settings. We find that model rankings from Copilot Arena differ from those of existing evaluations, which we attribute to the more realistic distribution of data and tasks contained in Copilot Arena. We also identify novel insights into human preferences on code such as an observed consistency in user preference across programming languages yet significant variation in preference due to task category. We open-source Copilot Arena and release data to enable human-centric evaluations and improve understanding of coding assistants. △ Less

Submitted 13 February, 2025; originally announced February 2025.

ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data

Authors: Junhong Shen, Atishay Jain, Zedian Xiao, Ishan Amlekar, Mouad Hadji, Aaron Podolny, Ameet Talwalkar

Abstract: Large Language Model (LLM) agents are rapidly improving to handle increasingly complex web-based tasks. Most of these agents rely on general-purpose, proprietary models like GPT-4 and focus on designing better prompts to improve their planning abilities. However, general-purpose LLMs are not specifically trained to understand specialized web contexts such as HTML, and they often struggle with long… ▽ More Large Language Model (LLM) agents are rapidly improving to handle increasingly complex web-based tasks. Most of these agents rely on general-purpose, proprietary models like GPT-4 and focus on designing better prompts to improve their planning abilities. However, general-purpose LLMs are not specifically trained to understand specialized web contexts such as HTML, and they often struggle with long-horizon planning. We explore an alternative approach that fine-tunes open-source LLMs using production-scale workflow data collected from over 250 domains corresponding to 6 billion tokens. This simple yet effective approach shows substantial gains over prompting-based agents on existing benchmarks -- ScribeAgent achieves state-of-the-art direct generation performance on Mind2Web and improves the task success rate by 7.3% over the previous best text-only web agents on WebArena. We further perform detailed ablation studies on various fine-tuning design choices and provide insights into LLM selection, training recipes, context window optimization, and effect of dataset sizes. △ Less

Submitted 4 December, 2024; v1 submitted 22 November, 2024; originally announced November 2024.

Specialized Foundation Models Struggle to Beat Supervised Baselines

Authors: Zongzhe Xu, Ritvik Gupta, Wenduo Cheng, Alexander Shen, Junhong Shen, Ameet Talwalkar, Mikhail Khodak

Abstract: Following its success for vision and text, the "foundation model" (FM) paradigm -- pretraining large models on massive data, then fine-tuning on target tasks -- has rapidly expanded to domains in the sciences, engineering, healthcare, and beyond. Has this achieved what the original FMs accomplished, i.e. the supplanting of traditional supervised learning in their domains? To answer we look at thre… ▽ More Following its success for vision and text, the "foundation model" (FM) paradigm -- pretraining large models on massive data, then fine-tuning on target tasks -- has rapidly expanded to domains in the sciences, engineering, healthcare, and beyond. Has this achieved what the original FMs accomplished, i.e. the supplanting of traditional supervised learning in their domains? To answer we look at three modalities -- genomics, satellite imaging, and time series -- with multiple recent FMs and compare them to a standard supervised learning workflow: model development, hyperparameter tuning, and training, all using only data from the target task. Across these three specialized domains, we find that it is consistently possible to train simple supervised models -- no more complicated than a lightly modified wide ResNet or UNet -- that match or even outperform the latest foundation models. Our work demonstrates that the benefits of large-scale pretraining have yet to be realized in many specialized areas, reinforces the need to compare new FMs to strong, well-tuned baselines, and introduces two new, easy-to-use, open-source, and automated workflows for doing so. △ Less

Submitted 20 March, 2025; v1 submitted 4 November, 2024; originally announced November 2024.

Comments: The first two authors contributed equally. The order was determined by coin flip

Understanding Optimization in Deep Learning with Central Flows

Authors: Jeremy M. Cohen, Alex Damian, Ameet Talwalkar, J. Zico Kolter, Jason D. Lee

Abstract: Traditional theories of optimization cannot describe the dynamics of optimization in deep learning, even in the simple setting of deterministic training. The challenge is that optimizers typically operate in a complex, oscillatory regime called the "edge of stability." In this paper, we develop theory that can describe the dynamics of optimization in this regime. Our key insight is that while the… ▽ More Traditional theories of optimization cannot describe the dynamics of optimization in deep learning, even in the simple setting of deterministic training. The challenge is that optimizers typically operate in a complex, oscillatory regime called the "edge of stability." In this paper, we develop theory that can describe the dynamics of optimization in this regime. Our key insight is that while the *exact* trajectory of an oscillatory optimizer may be challenging to analyze, the *time-averaged* (i.e. smoothed) trajectory is often much more tractable. To analyze an optimizer, we derive a differential equation called a "central flow" that characterizes this time-averaged trajectory. We empirically show that these central flows can predict long-term optimization trajectories for generic neural networks with a high degree of numerical accuracy. By interpreting these central flows, we are able to understand how gradient descent makes progress even as the loss sometimes goes up; how adaptive optimizers "adapt" to the local loss landscape; and how adaptive optimizers implicitly navigate towards regions where they can take larger steps. Our results suggest that central flows can be a valuable theoretical tool for reasoning about optimization in deep learning. △ Less

Submitted 25 September, 2025; v1 submitted 31 October, 2024; originally announced October 2024.

Comments: First two authors contributed equally; author order determined by coin flip. This is the full version of a paper published at ICLR 2025. We encourage readers to explore the blog version of this paper, with animated optimization trajectories, at https://centralflows.github.io. Our code can be found at https://github.com/centralflows/centralflows

Need Help? Designing Proactive AI Assistants for Programming

Authors: Valerie Chen, Alan Zhu, Sebastian Zhao, Hussein Mozannar, David Sontag, Ameet Talwalkar

Abstract: While current chat-based AI assistants primarily operate reactively, responding only when prompted by users, there is significant potential for these systems to proactively assist in tasks without explicit invocation, enabling a mixed-initiative interaction. This work explores the design and implementation of proactive AI assistants powered by large language models. We first outline the key design… ▽ More While current chat-based AI assistants primarily operate reactively, responding only when prompted by users, there is significant potential for these systems to proactively assist in tasks without explicit invocation, enabling a mixed-initiative interaction. This work explores the design and implementation of proactive AI assistants powered by large language models. We first outline the key design considerations for building effective proactive assistants. As a case study, we propose a proactive chat-based programming assistant that automatically provides suggestions and facilitates their integration into the programmer's code. The programming context provides a shared workspace enabling the assistant to offer more relevant suggestions. We conducted a randomized experimental study examining the impact of various design elements of the proactive assistant on programmer productivity and user experience. Our findings reveal significant benefits of incorporating proactive chat assistants into coding environments and uncover important nuances that influence their usage and effectiveness. △ Less

Submitted 28 February, 2025; v1 submitted 6 October, 2024; originally announced October 2024.

Comments: CHI 2025

The Impact of Element Ordering on LM Agent Performance

Authors: Wayne Chi, Ameet Talwalkar, Chris Donahue

Abstract: There has been a surge of interest in language model agents that can navigate virtual environments such as the web or desktop. To navigate such environments, agents benefit from information on the various elements (e.g., buttons, text, or images) present. It remains unclear which element attributes have the greatest impact on agent performance, especially in environments that only provide a graphi… ▽ More There has been a surge of interest in language model agents that can navigate virtual environments such as the web or desktop. To navigate such environments, agents benefit from information on the various elements (e.g., buttons, text, or images) present. It remains unclear which element attributes have the greatest impact on agent performance, especially in environments that only provide a graphical representation (i.e., pixels). Here we find that the ordering in which elements are presented to the language model is surprisingly impactful--randomizing element ordering in a webpage degrades agent performance comparably to removing all visible text from an agent's state representation. While a webpage provides a hierarchical ordering of elements, there is no such ordering when parsing elements directly from pixels. Moreover, as tasks become more challenging and models more sophisticated, our experiments suggest that the impact of ordering increases. Finding an effective ordering is non-trivial. We investigate the impact of various element ordering methods in web and desktop environments. We find that dimensionality reduction provides a viable ordering for pixel-only environments. We train a UI element detection model to derive elements from pixels and apply our findings to an agent benchmark--OmniACT--where we only have access to pixels. Our method completes more than two times as many tasks on average relative to the previous state-of-the-art. △ Less

Submitted 6 October, 2024; v1 submitted 18 September, 2024; originally announced September 2024.

Modulating Language Model Experiences through Frictions

Authors: Katherine M. Collins, Valerie Chen, Ilia Sucholutsky, Hannah Rose Kirk, Malak Sadek, Holli Sargeant, Ameet Talwalkar, Adrian Weller, Umang Bhatt

Abstract: Language models are transforming the ways that their users engage with the world. Despite impressive capabilities, over-consumption of language model outputs risks propagating unchecked errors in the short-term and damaging human capabilities for critical thinking in the long-term. How can we develop scaffolding around language models to curate more appropriate use? We propose selective frictions… ▽ More Language models are transforming the ways that their users engage with the world. Despite impressive capabilities, over-consumption of language model outputs risks propagating unchecked errors in the short-term and damaging human capabilities for critical thinking in the long-term. How can we develop scaffolding around language models to curate more appropriate use? We propose selective frictions for language model experiences, inspired by behavioral science interventions, to dampen misuse. Frictions involve small modifications to a user's experience, e.g., the addition of a button impeding model access and reminding a user of their expertise relative to the model. Through a user study with real humans, we observe shifts in user behavior from the imposition of a friction over LLMs in the context of a multi-topic question-answering task as a representative task that people may use LLMs for, e.g., in education and information retrieval. We find that frictions modulate over-reliance by driving down users' click rates while minimally affecting accuracy for those topics. Yet, frictions may have unintended effects. We find marked differences in users' click behaviors even on topics where frictions were not provisioned. Our contributions motivate further study of human-AI behavioral interaction to inform more effective and appropriate LLM use. △ Less

Submitted 18 November, 2024; v1 submitted 24 June, 2024; originally announced July 2024.

Comments: NeurIPS Workshop on Behavioral ML; non-archival

Agreement-Based Cascading for Efficient Inference

Authors: Steven Kolawole, Don Dennis, Ameet Talwalkar, Virginia Smith

Abstract: Adaptive inference schemes reduce the cost of machine learning inference by assigning smaller models to easier examples, attempting to avoid invocation of larger models when possible. In this work we explore a simple, effective adaptive inference technique we term Agreement-Based Cascading (ABC). ABC builds a cascade of models of increasing size/complexity, and uses agreement between ensembles of… ▽ More Adaptive inference schemes reduce the cost of machine learning inference by assigning smaller models to easier examples, attempting to avoid invocation of larger models when possible. In this work we explore a simple, effective adaptive inference technique we term Agreement-Based Cascading (ABC). ABC builds a cascade of models of increasing size/complexity, and uses agreement between ensembles of models at each level of the cascade as a basis for data-dependent routing. Although ensemble execution introduces additional expense, we show that these costs can be easily offset in practice due to large expected differences in model sizes, parallel inference execution capabilities, and accuracy benefits of ensembling. We examine ABC theoretically and empirically in terms of these parameters, showing that the approach can reliably act as a drop-in replacement for existing models and surpass the best single model it aims to replace in terms of both efficiency and accuracy. Additionally, we explore the performance of ABC relative to existing cascading methods in three common scenarios: (1) edge-to-cloud inference, where ABC reduces communication costs by up to 14x; (2) cloud-based model serving, where it achieves a 3x reduction in rental costs; and (3) inference via model API services, where ABC achieves a 2-25x reduction in average price per token/request relative to state-of-the-art LLM cascades. △ Less

Submitted 24 September, 2025; v1 submitted 2 July, 2024; originally announced July 2024.

Comments: Published at TMLR (July 2025)

Journal ref: TMLR 2025

The RealHumanEval: Evaluating Large Language Models' Abilities to Support Programmers

Authors: Hussein Mozannar, Valerie Chen, Mohammed Alsobay, Subhro Das, Sebastian Zhao, Dennis Wei, Manish Nagireddy, Prasanna Sattigeri, Ameet Talwalkar, David Sontag

Abstract: Evaluation of large language models for code has primarily relied on static benchmarks, including HumanEval (Chen et al., 2021), or more recently using human preferences of LLM responses. As LLMs are increasingly used as programmer assistants, we study whether gains on existing benchmarks or more preferred LLM responses translate to programmer productivity when coding with LLMs, including time spe… ▽ More Evaluation of large language models for code has primarily relied on static benchmarks, including HumanEval (Chen et al., 2021), or more recently using human preferences of LLM responses. As LLMs are increasingly used as programmer assistants, we study whether gains on existing benchmarks or more preferred LLM responses translate to programmer productivity when coding with LLMs, including time spent coding. We introduce RealHumanEval, a web interface to measure the ability of LLMs to assist programmers, through either autocomplete or chat support. We conducted a user study (N=243) using RealHumanEval in which users interacted with seven LLMs of varying base model performance. Despite static benchmarks not incorporating humans-in-the-loop, we find that improvements in benchmark performance lead to increased programmer productivity; however gaps in benchmark versus human performance are not proportional -- a trend that holds across both forms of LLM support. In contrast, we find that programmer preferences do not correlate with their actual performance, motivating the need for better proxy signals. We open-source RealHumanEval to enable human-centric evaluation of new models and the study data to facilitate efforts to improve code models. △ Less

Submitted 14 October, 2024; v1 submitted 3 April, 2024; originally announced April 2024.

UPS: Efficiently Building Foundation Models for PDE Solving via Cross-Modal Adaptation

Authors: Junhong Shen, Tanya Marwah, Ameet Talwalkar

Abstract: We present Unified PDE Solvers (UPS), a data- and compute-efficient approach to developing unified neural operators for diverse families of spatiotemporal PDEs from various domains, dimensions, and resolutions. UPS embeds different PDEs into a shared representation space and processes them using a FNO-transformer architecture. Rather than training the network from scratch, which is data-demanding… ▽ More We present Unified PDE Solvers (UPS), a data- and compute-efficient approach to developing unified neural operators for diverse families of spatiotemporal PDEs from various domains, dimensions, and resolutions. UPS embeds different PDEs into a shared representation space and processes them using a FNO-transformer architecture. Rather than training the network from scratch, which is data-demanding and computationally expensive, we warm-start the transformer from pretrained LLMs and perform explicit alignment to reduce the modality gap while improving data and compute efficiency. The cross-modal UPS achieves state-of-the-art results on a wide range of 1D and 2D PDE families from PDEBench, outperforming existing unified models using 4 times less data and 26 times less compute. Meanwhile, it is capable of few-shot transfer to unseen PDE families and coefficients. △ Less

Submitted 23 November, 2024; v1 submitted 11 March, 2024; originally announced March 2024.

Comments: TMLR 2024; ICML 2024 AI for Science Workshop (Spotlight)

Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes

Authors: Steven Kolawole, Lucio Dery, Jean-François Kagy, Virginia Smith, Graham Neubig, Ameet Talwalkar

Abstract: Structured pruning is a promising approach to create smaller, faster large language models. However, existing methods typically rely on computing the gradient via backward passes, which can inflate memory requirements and compute costs. In this work we introduce Bonsai, a gradient-free structured pruning method that eliminates the need for backpropagation, significantly reducing memory requirement… ▽ More Structured pruning is a promising approach to create smaller, faster large language models. However, existing methods typically rely on computing the gradient via backward passes, which can inflate memory requirements and compute costs. In this work we introduce Bonsai, a gradient-free structured pruning method that eliminates the need for backpropagation, significantly reducing memory requirements and compute costs while achieving state-of-the-art pruning performance. Bonsai uses forward-pass-only perturbative pruning to enable efficient compression of large models on a broader range of hardware configurations. Unlike existing structured pruning approaches, Bonsai not only achieves better compression with fewer resources but also produces models that are twice as fast as those generated by semi-structured pruning. As a concrete demonstration, we use Bonsai to prune 7B and 8B models to 50% sparsity on a single A6000 GPU -- a task challenging for backprop-based methods in memory-constrained settings, as they require 2-3x the memory. Our results show that removing backprop as a requirement not only enables pruning larger models on constrained hardware but can also lead to state-of-the-art efficiency and performance. △ Less

Submitted 22 January, 2026; v1 submitted 7 February, 2024; originally announced February 2024.

Comments: 19 pages, 6 fiigures, 16 tables

Multitask Learning Can Improve Worst-Group Outcomes

Authors: Atharva Kulkarni, Lucio Dery, Amrith Setlur, Aditi Raghunathan, Ameet Talwalkar, Graham Neubig

Abstract: In order to create machine learning systems that serve a variety of users well, it is vital to not only achieve high average performance but also ensure equitable outcomes across diverse groups. However, most machine learning methods are designed to improve a model's average performance on a chosen end task without consideration for their impact on worst group error. Multitask learning (MTL) is on… ▽ More In order to create machine learning systems that serve a variety of users well, it is vital to not only achieve high average performance but also ensure equitable outcomes across diverse groups. However, most machine learning methods are designed to improve a model's average performance on a chosen end task without consideration for their impact on worst group error. Multitask learning (MTL) is one such widely used technique. In this paper, we seek not only to understand the impact of MTL on worst-group accuracy but also to explore its potential as a tool to address the challenge of group-wise fairness. We primarily consider the standard setting of fine-tuning a pre-trained model, where, following recent work \citep{gururangan2020don, dery2023aang}, we multitask the end task with the pre-training objective constructed from the end task data itself. In settings with few or no group annotations, we find that multitasking often, but not consistently, achieves better worst-group accuracy than Just-Train-Twice (JTT; \citet{pmlr-v139-liu21f}) -- a representative distributionally robust optimization (DRO) method. Leveraging insights from synthetic data experiments, we propose to modify standard MTL by regularizing the joint multitask representation space. We run a large number of fine-tuning experiments across computer vision and natural language processing datasets and find that our regularized MTL approach \emph{consistently} outperforms JTT on both average and worst-group outcomes. Our official code can be found here: \href{https://github.com/atharvajk98/MTL-group-robustness.git}{\url{https://github.com/atharvajk98/MTL-group-robustness}}. △ Less

Submitted 28 February, 2024; v1 submitted 5 December, 2023; originally announced December 2023.

Comments: 20 pages, 7 tables, 6 Figures

Do LLMs exhibit human-like response biases? A case study in survey design

Authors: Lindia Tjuatja, Valerie Chen, Sherry Tongshuang Wu, Ameet Talwalkar, Graham Neubig

Abstract: As large language models (LLMs) become more capable, there is growing excitement about the possibility of using LLMs as proxies for humans in real-world tasks where subjective labels are desired, such as in surveys and opinion polling. One widely-cited barrier to the adoption of LLMs as proxies for humans in subjective tasks is their sensitivity to prompt wording - but interestingly, humans also d… ▽ More As large language models (LLMs) become more capable, there is growing excitement about the possibility of using LLMs as proxies for humans in real-world tasks where subjective labels are desired, such as in surveys and opinion polling. One widely-cited barrier to the adoption of LLMs as proxies for humans in subjective tasks is their sensitivity to prompt wording - but interestingly, humans also display sensitivities to instruction changes in the form of response biases. We investigate the extent to which LLMs reflect human response biases, if at all. We look to survey design, where human response biases caused by changes in the wordings of "prompts" have been extensively explored in social psychology literature. Drawing from these works, we design a dataset and framework to evaluate whether LLMs exhibit human-like response biases in survey questionnaires. Our comprehensive evaluation of nine models shows that popular open and commercial LLMs generally fail to reflect human-like behavior, particularly in models that have undergone RLHF. Furthermore, even if a model shows a significant change in the same direction as humans, we find that they are sensitive to perturbations that do not elicit significant changes in humans. These results highlight the pitfalls of using LLMs as human proxies, and underscore the need for finer-grained characterizations of model behavior. Our code, dataset, and collected samples are available at https://github.com/lindiatjuatja/BiasMonkey △ Less

Submitted 5 February, 2024; v1 submitted 7 November, 2023; originally announced November 2023.

Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances

Authors: Mikhail Khodak, Edmond Chow, Maria-Florina Balcan, Ameet Talwalkar

Abstract: Solving a linear system $Ax=b$ is a fundamental scientific computing primitive for which numerous solvers and preconditioners have been developed. These come with parameters whose optimal values depend on the system being solved and are often impossible or too expensive to identify; thus in practice sub-optimal heuristics are used. We consider the common setting in which many related linear system… ▽ More Solving a linear system $Ax=b$ is a fundamental scientific computing primitive for which numerous solvers and preconditioners have been developed. These come with parameters whose optimal values depend on the system being solved and are often impossible or too expensive to identify; thus in practice sub-optimal heuristics are used. We consider the common setting in which many related linear systems need to be solved, e.g. during a single numerical simulation. In this scenario, can we sequentially choose parameters that attain a near-optimal overall number of iterations, without extra matrix computations? We answer in the affirmative for Successive Over-Relaxation (SOR), a standard solver whose parameter $ω$ has a strong impact on its runtime. For this method, we prove that a bandit online learning algorithm--using only the number of iterations as feedback--can select parameters for a sequence of instances such that the overall cost approaches that of the best fixed $ω$ as the sequence length increases. Furthermore, when given additional structural information, we show that a contextual bandit method asymptotically achieves the performance of the instance-optimal policy, which selects the best $ω$ for each instance. Our work provides the first learning-theoretic treatment of high-precision linear system solvers and the first end-to-end guarantees for data-driven scientific computing, demonstrating theoretically the potential to speed up numerical methods using well-understood learning algorithms. △ Less

Submitted 2 May, 2024; v1 submitted 3 October, 2023; originally announced October 2023.

Comments: ICLR 2024 Spotlight

FeedbackLogs: Recording and Incorporating Stakeholder Feedback into Machine Learning Pipelines

Authors: Matthew Barker, Emma Kallina, Dhananjay Ashok, Katherine M. Collins, Ashley Casovan, Adrian Weller, Ameet Talwalkar, Valerie Chen, Umang Bhatt

Abstract: Even though machine learning (ML) pipelines affect an increasing array of stakeholders, there is little work on how input from stakeholders is recorded and incorporated. We propose FeedbackLogs, addenda to existing documentation of ML pipelines, to track the input of multiple stakeholders. Each log records important details about the feedback collection process, the feedback itself, and how the fe… ▽ More Even though machine learning (ML) pipelines affect an increasing array of stakeholders, there is little work on how input from stakeholders is recorded and incorporated. We propose FeedbackLogs, addenda to existing documentation of ML pipelines, to track the input of multiple stakeholders. Each log records important details about the feedback collection process, the feedback itself, and how the feedback is used to update the ML pipeline. In this paper, we introduce and formalise a process for collecting a FeedbackLog. We also provide concrete use cases where FeedbackLogs can be employed as evidence for algorithmic auditing and as a tool to record updates based on stakeholder feedback. △ Less

Submitted 28 July, 2023; originally announced July 2023.

Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms

Authors: Nari Johnson, Ángel Alexander Cabrera, Gregory Plumb, Ameet Talwalkar

Abstract: Machine learning (ML) models that achieve high average accuracy can still underperform on semantically coherent subsets ("slices") of data. This behavior can have significant societal consequences for the safety or bias of the model in deployment, but identifying these underperforming slices can be difficult in practice, especially in domains where practitioners lack access to group annotations to… ▽ More Machine learning (ML) models that achieve high average accuracy can still underperform on semantically coherent subsets ("slices") of data. This behavior can have significant societal consequences for the safety or bias of the model in deployment, but identifying these underperforming slices can be difficult in practice, especially in domains where practitioners lack access to group annotations to define coherent subsets of their data. Motivated by these challenges, ML researchers have developed new slice discovery algorithms that aim to group together coherent and high-error subsets of data. However, there has been little evaluation focused on whether these tools help humans form correct hypotheses about where (for which groups) their model underperforms. We conduct a controlled user study (N = 15) where we show 40 slices output by two state-of-the-art slice discovery algorithms to users, and ask them to form hypotheses about an object detection model. Our results provide positive evidence that these tools provide some benefit over a naive baseline, and also shed light on challenges faced by users during the hypothesis formation step. We conclude by discussing design opportunities for ML and HCI researchers. Our findings point to the importance of centering users when creating and evaluating new tools for slice discovery. △ Less

Submitted 9 February, 2024; v1 submitted 13 June, 2023; originally announced June 2023.

Comments: Proceedings of the AAAI Conference on Human Computation and Crowdsourcing, 11(1), 65-76. Best Paper Award

Learning Personalized Decision Support Policies

Authors: Umang Bhatt, Valerie Chen, Katherine M. Collins, Parameswaran Kamalaruban, Emma Kallina, Adrian Weller, Ameet Talwalkar

Abstract: Individual human decision-makers may benefit from different forms of support to improve decision outcomes, but when each form of support will yield better outcomes? In this work, we posit that personalizing access to decision support tools can be an effective mechanism for instantiating the appropriate use of AI assistance. Specifically, we propose the general problem of learning a decision suppor… ▽ More Individual human decision-makers may benefit from different forms of support to improve decision outcomes, but when each form of support will yield better outcomes? In this work, we posit that personalizing access to decision support tools can be an effective mechanism for instantiating the appropriate use of AI assistance. Specifically, we propose the general problem of learning a decision support policy that, for a given input, chooses which form of support to provide to decision-makers for whom we initially have no prior information. We develop $\texttt{Modiste}$, an interactive tool to learn personalized decision support policies. $\texttt{Modiste}$ leverages stochastic contextual bandit techniques to personalize a decision support policy for each decision-maker and supports extensions to the multi-objective setting to account for auxiliary objectives like the cost of support. We find that personalized policies outperform offline policies, and, in the cost-aware setting, reduce the incurred cost with minimal degradation to performance. Our experiments include various realistic forms of support (e.g., expert consensus and predictions from a large language model) on vision and language tasks. Our human subject experiments validate our computational experiments, demonstrating that personalization can yield benefits in practice for real users, who interact with $\texttt{Modiste}$. △ Less

Submitted 23 January, 2025; v1 submitted 13 April, 2023; originally announced April 2023.

Comments: AAAI 2025

Assisting Human Decisions in Document Matching

Authors: Joon Sik Kim, Valerie Chen, Danish Pruthi, Nihar B. Shah, Ameet Talwalkar

Abstract: Many practical applications, ranging from paper-reviewer assignment in peer review to job-applicant matching for hiring, require human decision makers to identify relevant matches by combining their expertise with predictions from machine learning models. In many such model-assisted document matching tasks, the decision makers have stressed the need for assistive information about the model output… ▽ More Many practical applications, ranging from paper-reviewer assignment in peer review to job-applicant matching for hiring, require human decision makers to identify relevant matches by combining their expertise with predictions from machine learning models. In many such model-assisted document matching tasks, the decision makers have stressed the need for assistive information about the model outputs (or the data) to facilitate their decisions. In this paper, we devise a proxy matching task that allows us to evaluate which kinds of assistive information improve decision makers' performance (in terms of accuracy and time). Through a crowdsourced (N=271 participants) study, we find that providing black-box model explanations reduces users' accuracy on the matching task, contrary to the commonly-held belief that they can be helpful by allowing better understanding of the model. On the other hand, custom methods that are designed to closely attend to some task-specific desiderata are found to be effective in improving user performance. Surprisingly, we also find that the users' perceived utility of assistive information is misaligned with their objective utility (measured through their task performance). △ Less

Submitted 16 February, 2023; originally announced February 2023.

Cross-Modal Fine-Tuning: Align then Refine

Authors: Junhong Shen, Liam Li, Lucio M. Dery, Corey Staten, Mikhail Khodak, Graham Neubig, Ameet Talwalkar

Abstract: Fine-tuning large-scale pretrained models has led to tremendous progress in well-studied modalities such as vision and NLP. However, similar gains have not been observed in many other modalities due to a lack of relevant pretrained models. In this work, we propose ORCA, a general cross-modal fine-tuning framework that extends the applicability of a single large-scale pretrained model to diverse mo… ▽ More Fine-tuning large-scale pretrained models has led to tremendous progress in well-studied modalities such as vision and NLP. However, similar gains have not been observed in many other modalities due to a lack of relevant pretrained models. In this work, we propose ORCA, a general cross-modal fine-tuning framework that extends the applicability of a single large-scale pretrained model to diverse modalities. ORCA adapts to a target task via an align-then-refine workflow: given the target input, ORCA first learns an embedding network that aligns the embedded feature distribution with the pretraining modality. The pretrained model is then fine-tuned on the embedded data to exploit the knowledge shared across modalities. Through extensive experiments, we show that ORCA obtains state-of-the-art results on 3 benchmarks containing over 60 datasets from 12 modalities, outperforming a wide range of hand-designed, AutoML, general-purpose, and task-specific methods. We highlight the importance of data alignment via a series of ablation studies and demonstrate ORCA's utility in data-limited regimes. △ Less

Submitted 18 March, 2023; v1 submitted 11 February, 2023; originally announced February 2023.

Zeno: An Interactive Framework for Behavioral Evaluation of Machine Learning

Authors: Ángel Alexander Cabrera, Erica Fu, Donald Bertucci, Kenneth Holstein, Ameet Talwalkar, Jason I. Hong, Adam Perer

Abstract: Machine learning models with high accuracy on test data can still produce systematic failures, such as harmful biases and safety issues, when deployed in the real world. To detect and mitigate such failures, practitioners run behavioral evaluation of their models, checking model outputs for specific types of inputs. Behavioral evaluation is important but challenging, requiring that practitioners d… ▽ More Machine learning models with high accuracy on test data can still produce systematic failures, such as harmful biases and safety issues, when deployed in the real world. To detect and mitigate such failures, practitioners run behavioral evaluation of their models, checking model outputs for specific types of inputs. Behavioral evaluation is important but challenging, requiring that practitioners discover real-world patterns and validate systematic failures. We conducted 18 semi-structured interviews with ML practitioners to better understand the challenges of behavioral evaluation and found that it is a collaborative, use-case-first process that is not adequately supported by existing task- and domain-specific tools. Using these findings, we designed Zeno, a general-purpose framework for visualizing and testing AI systems across diverse use cases. In four case studies with participants using Zeno on real-world models, we found that practitioners were able to reproduce previous manual analyses and discover new systematic failures. △ Less

Submitted 9 February, 2023; originally announced February 2023.

On Noisy Evaluation in Federated Hyperparameter Tuning

Authors: Kevin Kuo, Pratiksha Thaker, Mikhail Khodak, John Nguyen, Daniel Jiang, Ameet Talwalkar, Virginia Smith

Abstract: Hyperparameter tuning is critical to the success of federated learning applications. Unfortunately, appropriately selecting hyperparameters is challenging in federated networks. Issues of scale, privacy, and heterogeneity introduce noise in the tuning process and make it difficult to evaluate the performance of various hyperparameters. In this work, we perform the first systematic study on the eff… ▽ More Hyperparameter tuning is critical to the success of federated learning applications. Unfortunately, appropriately selecting hyperparameters is challenging in federated networks. Issues of scale, privacy, and heterogeneity introduce noise in the tuning process and make it difficult to evaluate the performance of various hyperparameters. In this work, we perform the first systematic study on the effect of noisy evaluation in federated hyperparameter tuning. We first identify and rigorously explore key sources of noise, including client subsampling, data and systems heterogeneity, and data privacy. Surprisingly, our results indicate that even small amounts of noise can significantly impact tuning methods-reducing the performance of state-of-the-art approaches to that of naive baselines. To address noisy evaluation in such scenarios, we propose a simple and effective approach that leverages public proxy data to boost the evaluation signal. Our work establishes general challenges, baselines, and best practices for future work in federated hyperparameter tuning. △ Less

Submitted 15 May, 2023; v1 submitted 17 December, 2022; originally announced December 2022.

Comments: v1: 19 pages, 15 figures, submitted to MLSys2023; v2: Fixed citation formatting; v3: Fixed typo, update acks v4: MLSys2023 camera-ready

AutoML for Climate Change: A Call to Action

Authors: Renbo Tu, Nicholas Roberts, Vishak Prasad, Sibasis Nayak, Paarth Jain, Frederic Sala, Ganesh Ramakrishnan, Ameet Talwalkar, Willie Neiswanger, Colin White

Abstract: The challenge that climate change poses to humanity has spurred a rapidly developing field of artificial intelligence research focused on climate change applications. The climate change AI (CCAI) community works on a diverse, challenging set of problems which often involve physics-constrained ML or heterogeneous spatiotemporal data. It would be desirable to use automated machine learning (AutoML)… ▽ More The challenge that climate change poses to humanity has spurred a rapidly developing field of artificial intelligence research focused on climate change applications. The climate change AI (CCAI) community works on a diverse, challenging set of problems which often involve physics-constrained ML or heterogeneous spatiotemporal data. It would be desirable to use automated machine learning (AutoML) techniques to automatically find high-performing architectures and hyperparameters for a given dataset. In this work, we benchmark popular AutoML libraries on three high-leverage CCAI applications: climate modeling, wind power forecasting, and catalyst discovery. We find that out-of-the-box AutoML libraries currently fail to meaningfully surpass the performance of human-designed CCAI models. However, we also identify a few key weaknesses, which stem from the fact that most AutoML techniques are tailored to computer vision and NLP applications. For example, while dozens of search spaces have been designed for image and language data, none have been designed for spatiotemporal data. Addressing these key weaknesses can lead to the discovery of novel architectures that yield substantial performance gains across numerous CCAI applications. Therefore, we present a call to action to the AutoML community, since there are a number of concrete, promising directions for future work in the space of AutoML for CCAI. We release our code and a list of resources at https://github.com/climate-change-automl/climate-change-automl. △ Less

Submitted 7 October, 2022; originally announced October 2022.

SONAR: Joint Architecture and System Optimization Search

Authors: Elias Jääsaari, Michelle Ma, Ameet Talwalkar, Tianqi Chen

Abstract: There is a growing need to deploy machine learning for different tasks on a wide array of new hardware platforms. Such deployment scenarios require tackling multiple challenges, including identifying a model architecture that can achieve a suitable predictive accuracy (architecture search), and finding an efficient implementation of the model to satisfy underlying hardware-specific systems constra… ▽ More There is a growing need to deploy machine learning for different tasks on a wide array of new hardware platforms. Such deployment scenarios require tackling multiple challenges, including identifying a model architecture that can achieve a suitable predictive accuracy (architecture search), and finding an efficient implementation of the model to satisfy underlying hardware-specific systems constraints such as latency (system optimization search). Existing works treat architecture search and system optimization search as separate problems and solve them sequentially. In this paper, we instead propose to solve these problems jointly, and introduce a simple but effective baseline method called SONAR that interleaves these two search problems. SONAR aims to efficiently optimize for predictive accuracy and inference latency by applying early stopping to both search processes. Our experiments on multiple different hardware back-ends show that SONAR identifies nearly optimal architectures 30 times faster than a brute force approach. △ Less

Submitted 25 August, 2022; originally announced August 2022.

Provably tuning the ElasticNet across instances

Authors: Maria-Florina Balcan, Mikhail Khodak, Dravyansh Sharma, Ameet Talwalkar

Abstract: An important unresolved challenge in the theory of regularization is to set the regularization coefficients of popular techniques like the ElasticNet with general provable guarantees. We consider the problem of tuning the regularization parameters of Ridge regression, LASSO, and the ElasticNet across multiple problem instances, a setting that encompasses both cross-validation and multi-task hyperp… ▽ More An important unresolved challenge in the theory of regularization is to set the regularization coefficients of popular techniques like the ElasticNet with general provable guarantees. We consider the problem of tuning the regularization parameters of Ridge regression, LASSO, and the ElasticNet across multiple problem instances, a setting that encompasses both cross-validation and multi-task hyperparameter optimization. We obtain a novel structural result for the ElasticNet which characterizes the loss as a function of the tuning parameters as a piecewise-rational function with algebraic boundaries. We use this to bound the structural complexity of the regularized loss functions and show generalization guarantees for tuning the ElasticNet regression coefficients in the statistical setting. We also consider the more challenging online learning setting, where we show vanishing average expected regret relative to the optimal parameter pair. We further extend our results to tuning classification algorithms obtained by thresholding regression fits regularized by Ridge, LASSO, or ElasticNet. Our results are the first general learning-theoretic guarantees for this important class of problems that avoid strong assumptions on the data distribution. Furthermore, our guarantees hold for both validation and popular information criterion objectives. △ Less

Submitted 15 January, 2024; v1 submitted 20 July, 2022; originally announced July 2022.

Towards a More Rigorous Science of Blindspot Discovery in Image Classification Models

Authors: Gregory Plumb, Nari Johnson, Ángel Alexander Cabrera, Ameet Talwalkar

Abstract: A growing body of work studies Blindspot Discovery Methods ("BDM"s): methods that use an image embedding to find semantically meaningful (i.e., united by a human-understandable concept) subsets of the data where an image classifier performs significantly worse. Motivated by observed gaps in prior work, we introduce a new framework for evaluating BDMs, SpotCheck, that uses synthetic image datasets… ▽ More A growing body of work studies Blindspot Discovery Methods ("BDM"s): methods that use an image embedding to find semantically meaningful (i.e., united by a human-understandable concept) subsets of the data where an image classifier performs significantly worse. Motivated by observed gaps in prior work, we introduce a new framework for evaluating BDMs, SpotCheck, that uses synthetic image datasets to train models with known blindspots and a new BDM, PlaneSpot, that uses a 2D image representation. We use SpotCheck to run controlled experiments that identify factors that influence BDM performance (e.g., the number of blindspots in a model, or features used to define the blindspot) and show that PlaneSpot is competitive with and in many cases outperforms existing BDMs. Importantly, we validate these findings by designing additional experiments that use real image data from MS-COCO, a large image benchmark dataset. Our findings suggest several promising directions for future work on BDM design and evaluation. Overall, we hope that the methodology and analyses presented in this work will help facilitate a more rigorous science of blindspot discovery. △ Less

Submitted 11 July, 2023; v1 submitted 8 July, 2022; originally announced July 2022.

Comments: reviewed on OpenReview: https://openreview.net/forum?id=MaDvbLaBiF

Journal ref: TMLR 2023

On the Importance of Application-Grounded Experimental Design for Evaluating Explainable ML Methods

Authors: Kasun Amarasinghe, Kit T. Rodolfa, Sérgio Jesus, Valerie Chen, Vladimir Balayan, Pedro Saleiro, Pedro Bizarro, Ameet Talwalkar, Rayid Ghani

Abstract: Most existing evaluations of explainable machine learning (ML) methods rely on simplifying assumptions or proxies that do not reflect real-world use cases; the handful of more robust evaluations on real-world settings have shortcomings in their design, resulting in limited conclusions of methods' real-world utility. In this work, we seek to bridge this gap by conducting a study that evaluates thre… ▽ More Most existing evaluations of explainable machine learning (ML) methods rely on simplifying assumptions or proxies that do not reflect real-world use cases; the handful of more robust evaluations on real-world settings have shortcomings in their design, resulting in limited conclusions of methods' real-world utility. In this work, we seek to bridge this gap by conducting a study that evaluates three popular explainable ML methods in a setting consistent with the intended deployment context. We build on a previous study on e-commerce fraud detection and make crucial modifications to its setup relaxing the simplifying assumptions made in the original work that departed from the deployment context. In doing so, we draw drastically different conclusions from the earlier work and find no evidence for the incremental utility of the tested methods in the task. Our results highlight how seemingly trivial experimental design choices can yield misleading conclusions, with lessons about the necessity of not only evaluating explainable ML methods using tasks, data, users, and metrics grounded in the intended deployment contexts but also developing methods tailored to specific applications. In addition, we believe the design of this experiment can serve as a template for future study designs evaluating explainable ML methods in other real-world contexts. △ Less

Submitted 21 February, 2023; v1 submitted 24 June, 2022; originally announced June 2022.

Use-Case-Grounded Simulations for Explanation Evaluation

Authors: Valerie Chen, Nari Johnson, Nicholay Topin, Gregory Plumb, Ameet Talwalkar

Abstract: A growing body of research runs human subject evaluations to study whether providing users with explanations of machine learning models can help them with practical real-world use cases. However, running user studies is challenging and costly, and consequently each study typically only evaluates a limited number of different settings, e.g., studies often only evaluate a few arbitrarily selected ex… ▽ More A growing body of research runs human subject evaluations to study whether providing users with explanations of machine learning models can help them with practical real-world use cases. However, running user studies is challenging and costly, and consequently each study typically only evaluates a limited number of different settings, e.g., studies often only evaluate a few arbitrarily selected explanation methods. To address these challenges and aid user study design, we introduce Use-Case-Grounded Simulated Evaluations (SimEvals). SimEvals involve training algorithmic agents that take as input the information content (such as model explanations) that would be presented to each participant in a human subject study, to predict answers to the use case of interest. The algorithmic agent's test set accuracy provides a measure of the predictiveness of the information content for the downstream use case. We run a comprehensive evaluation on three real-world use cases (forward simulation, model debugging, and counterfactual reasoning) to demonstrate that Simevals can effectively identify which explanation methods will help humans for each use case. These results provide evidence that SimEvals can be used to efficiently screen an important set of user study design decisions, e.g. selecting which explanations should be presented to the user, before running a potentially costly user study. △ Less

Submitted 20 August, 2022; v1 submitted 5 June, 2022; originally announced June 2022.

AANG: Automating Auxiliary Learning

Authors: Lucio M. Dery, Paul Michel, Mikhail Khodak, Graham Neubig, Ameet Talwalkar

Abstract: Auxiliary objectives, supplementary learning signals that are introduced to help aid learning on data-starved or highly complex end-tasks, are commonplace in machine learning. Whilst much work has been done to formulate useful auxiliary objectives, their construction is still an art which proceeds by slow and tedious hand-design. Intuition for how and when these objectives improve end-task perform… ▽ More Auxiliary objectives, supplementary learning signals that are introduced to help aid learning on data-starved or highly complex end-tasks, are commonplace in machine learning. Whilst much work has been done to formulate useful auxiliary objectives, their construction is still an art which proceeds by slow and tedious hand-design. Intuition for how and when these objectives improve end-task performance has also had limited theoretical backing. In this work, we present an approach for automatically generating a suite of auxiliary objectives. We achieve this by deconstructing existing objectives within a novel unified taxonomy, identifying connections between them, and generating new ones based on the uncovered structure. Next, we theoretically formalize widely-held intuitions about how auxiliary learning improves generalization on the end-task. This leads us to a principled and efficient algorithm for searching the space of generated objectives to find those most useful to a specified end-task. With natural language processing (NLP) as our domain of study, we demonstrate that our automated auxiliary learning pipeline leads to strong improvements over competitive baselines across continued training experiments on a pre-trained model on 5 NLP tasks. △ Less

Submitted 27 February, 2023; v1 submitted 27 May, 2022; originally announced May 2022.

Comments: Accepted to ICLR 2023 22 pages, 7 tables and 5 figures

Perspectives on Incorporating Expert Feedback into Model Updates

Authors: Valerie Chen, Umang Bhatt, Hoda Heidari, Adrian Weller, Ameet Talwalkar

Abstract: Machine learning (ML) practitioners are increasingly tasked with developing models that are aligned with non-technical experts' values and goals. However, there has been insufficient consideration on how practitioners should translate domain expertise into ML updates. In this paper, we consider how to capture interactions between practitioners and experts systematically. We devise a taxonomy to ma… ▽ More Machine learning (ML) practitioners are increasingly tasked with developing models that are aligned with non-technical experts' values and goals. However, there has been insufficient consideration on how practitioners should translate domain expertise into ML updates. In this paper, we consider how to capture interactions between practitioners and experts systematically. We devise a taxonomy to match expert feedback types with practitioner updates. A practitioner may receive feedback from an expert at the observation- or domain-level, and convert this feedback into updates to the dataset, loss function, or parameter space. We review existing work from ML and human-computer interaction to describe this feedback-update taxonomy, and highlight the insufficient consideration given to incorporating feedback from non-technical experts. We end with a set of open questions that naturally arise from our proposed taxonomy and subsequent survey. △ Less

Submitted 16 July, 2022; v1 submitted 13 May, 2022; originally announced May 2022.

Efficient Architecture Search for Diverse Tasks

Authors: Junhong Shen, Mikhail Khodak, Ameet Talwalkar

Abstract: While neural architecture search (NAS) has enabled automated machine learning (AutoML) for well-researched areas, its application to tasks beyond computer vision is still under-explored. As less-studied domains are precisely those where we expect AutoML to have the greatest impact, in this work we study NAS for efficiently solving diverse problems. Seeking an approach that is fast, simple, and bro… ▽ More While neural architecture search (NAS) has enabled automated machine learning (AutoML) for well-researched areas, its application to tasks beyond computer vision is still under-explored. As less-studied domains are precisely those where we expect AutoML to have the greatest impact, in this work we study NAS for efficiently solving diverse problems. Seeking an approach that is fast, simple, and broadly applicable, we fix a standard convolutional network (CNN) topology and propose to search for the right kernel sizes and dilations its operations should take on. This dramatically expands the model's capacity to extract features at multiple resolutions for different types of data while only requiring search over the operation space. To overcome the efficiency challenges of naive weight-sharing in this search space, we introduce DASH, a differentiable NAS algorithm that computes the mixture-of-operations using the Fourier diagonalization of convolution, achieving both a better asymptotic complexity and an up-to-10x search time speedup in practice. We evaluate DASH on ten tasks spanning a variety of application domains such as PDE solving, protein folding, and heart disease detection. DASH outperforms state-of-the-art AutoML methods in aggregate, attaining the best-known automated performance on seven tasks. Meanwhile, on six of the ten tasks, the combined search and retraining time is less than 2x slower than simply training a CNN backbone that is far less accurate. △ Less

Submitted 9 October, 2022; v1 submitted 15 April, 2022; originally announced April 2022.

Comments: NeurIPS 2022 Camera-Ready; code available at https://github.com/sjunhongshen/DASH

Learning Predictions for Algorithms with Predictions

Authors: Mikhail Khodak, Maria-Florina Balcan, Ameet Talwalkar, Sergei Vassilvitskii

Abstract: A burgeoning paradigm in algorithm design is the field of algorithms with predictions, in which algorithms can take advantage of a possibly-imperfect prediction of some aspect of the problem. While much work has focused on using predictions to improve competitive ratios, running times, or other performance measures, less effort has been devoted to the question of how to obtain the predictions them… ▽ More A burgeoning paradigm in algorithm design is the field of algorithms with predictions, in which algorithms can take advantage of a possibly-imperfect prediction of some aspect of the problem. While much work has focused on using predictions to improve competitive ratios, running times, or other performance measures, less effort has been devoted to the question of how to obtain the predictions themselves, especially in the critical online setting. We introduce a general design approach for algorithms that learn predictors: (1) identify a functional dependence of the performance measure on the prediction quality and (2) apply techniques from online learning to learn predictors, tune robustness-consistency trade-offs, and bound the sample complexity. We demonstrate the effectiveness of our approach by applying it to bipartite matching, ski-rental, page migration, and job scheduling. In several settings we improve upon multiple existing results while utilizing a much simpler analysis, while in the others we provide the first learning-theoretic guarantees. △ Less

Submitted 17 October, 2022; v1 submitted 18 February, 2022; originally announced February 2022.

Comments: NeurIPS 2022 camera-ready