Showing 1–50 of 81 results for author: Miller, S

Proof of the hiding conjecture for Gaussian boson sampling with an arbitrary number of squeezed input modes

Authors: Laura Shou, Alexey V. Gorshkov, Victor Galitski, Sarah H. Miller

Abstract: Gaussian boson sampling (GBS) is a sampling task proposed to demonstrate quantum advantage. We consider Gaussian boson sampling on $M$ optical modes, with $K$ equally squeezed input modes and $N$ observed photon counts. We complete the proof of the hiding conjecture for Gaussian boson sampling with an arbitrary number of squeezers $K$, which is a part of the argument for classical hardness of GBS.… ▽ More Gaussian boson sampling (GBS) is a sampling task proposed to demonstrate quantum advantage. We consider Gaussian boson sampling on $M$ optical modes, with $K$ equally squeezed input modes and $N$ observed photon counts. We complete the proof of the hiding conjecture for Gaussian boson sampling with an arbitrary number of squeezers $K$, which is a part of the argument for classical hardness of GBS. In particular, we show that for any $K$ and $N=o(\sqrt{K})$, the symmetric product $MK^{-1/2}U_{NK}U_{NK}^T$, for $U_{NK}$ the top left $N\times K$ submatrix of an $M\times M$ Haar random unitary $U$, is close in total variation distance to both an $N\times N$ symmetric complex Gaussian matrix $\mathbf G$ with independent entries, and the symmetric product $GG^T/\sqrt{K}$ for $G$ an $N\times K$ matrix of iid standard complex Gaussians. We show however that the density-based instance generating method of [Aaronson and Arkhipov, Theory Comput. 9, 143 (2013), Lemma 5.8] used to efficiently implement a hiding procedure fails for Gaussian boson sampling with $K=cM$ if $c<1/2$. Instead we use approximate instance generating to implement the hiding for the usual classical hardness reduction. △ Less

Submitted 19 August, 2026; originally announced August 2026.

Comments: 25 pages, 1 figure

WorkBench Revisited: Workplace Agents Two Years On

Authors: Olly Styles, Sam Miller

Abstract: The best agent on WorkBench in March 2024, GPT-4, completed just 43% of tasks. We revisit the benchmark in June 2026 and find that the best agent to date, Claude Fable 5, now completes 98%. Beyond this considerable progress in frontier agent performance, three things stand out. First, unintended harmful actions, such as emailing the wrong person, fell from 26% of tasks for GPT-4 to 1.9% for Claude… ▽ More The best agent on WorkBench in March 2024, GPT-4, completed just 43% of tasks. We revisit the benchmark in June 2026 and find that the best agent to date, Claude Fable 5, now completes 98%. Beyond this considerable progress in frontier agent performance, three things stand out. First, unintended harmful actions, such as emailing the wrong person, fell from 26% of tasks for GPT-4 to 1.9% for Claude Fable 5; capability and safety go together on WorkBench rather than trade off, so the models that finish the most tasks also do the least unintended damage. Second, the rise of open-weight models has drastically lowered costs for a performance level that was only accessible to proprietary models, while frontier costs have stayed stable. Third, while several classes of error have been eliminated, frontier models still make some basic mistakes that occasionally result in irreversible harm. We release an updated version of the benchmark with data and code quality improvements, new model scores, and analysis of agent progress on WorkBench since 2024. △ Less

Submitted 1 July, 2026; v1 submitted 10 June, 2026; originally announced June 2026.

Comments: 8 pages, 3 figures. Follow-up to arXiv:2405.00823

Benchmarks in Leipzig

Authors: Andrei Balakin, Miklós Bóna, Marie-Charlotte Brandenburg, Clara Briand, Veronica Calvo Cortes, Shelby Cox, Jesus A. De Loera, Danai Deligeorgaki, Hannah Friedman, Tim Gehrunger, Chiara Giardino, Stephen Griffeth, Baran Hashemi, Elena Hoster, Alexander Ivanov, Nupur Jain, Aryaman Jal, Leonie Kayser, Joris Koefler, Kevin Kühn, Mario Kummer, Felix Lotter, René Marczinzik, Victor S. Miller, Alejandro Morales , et al. (23 additional authors not shown)

Abstract: Between April 1 and May 15, 2026, a group of 49 mathematicians compiled a dataset of research-level mathematics questions with known answers. Most of the work was done during the 3-day workshop *Benchmarks in Leipzig* with 35 participants at the Max Planck Institute for Mathematics in the Sciences in Leipzig, Germany. We present the resulting collection of 100 questions. We evaluated these questio… ▽ More Between April 1 and May 15, 2026, a group of 49 mathematicians compiled a dataset of research-level mathematics questions with known answers. Most of the work was done during the 3-day workshop *Benchmarks in Leipzig* with 35 participants at the Max Planck Institute for Mathematics in the Sciences in Leipzig, Germany. We present the resulting collection of 100 questions. We evaluated these questions in three stages: a single attempt by five state-of-the-art LLMs, followed by a 20-runs-per-model evaluation with three of these models, and finally a 3-run attempt with two heavy-thinking models. After Stage 1, 41 questions remained completely unsolved; after Stage 2, this count dropped to 16; and we concluded Stage 3 with only 2 unsolved questions. This demonstrates that the mathematical reasoning capabilities of LLMs are becoming impressive. △ Less

Submitted 4 June, 2026; originally announced June 2026.

Comments: 8 pages including 8 benchmark statistics tables + 20 pages appendix containing the 100 Leipzig Benchmark questions

Stochastic global optimization of continuous functions via random walks on Grassmannians

Authors: Kartik Gupta, Stephen D. Miller, Pradeep Ravikumar, Ramarathnam Venkatesan

Abstract: We introduce a stochastic global optimization method based on random walks on Grassmannian manifolds. To minimize a continuous objective $\ell:\mathbb{R}^d\rightarrow\mathbb{R}$, the method repeatedly samples random $k$-dimensional linear subspaces (with $k\ll d$), solves the resulting low-dimensional restrictions of these problems to these subspaces using an arbitrary black-box optimizer, and upd… ▽ More We introduce a stochastic global optimization method based on random walks on Grassmannian manifolds. To minimize a continuous objective $\ell:\mathbb{R}^d\rightarrow\mathbb{R}$, the method repeatedly samples random $k$-dimensional linear subspaces (with $k\ll d$), solves the resulting low-dimensional restrictions of these problems to these subspaces using an arbitrary black-box optimizer, and updates the iterate (which monotonically improves upon the previous iterate). Unlike classical optimization analyses that rely on convexity, smoothness, Lipschitz bounds, or Polyak-Lojasiewicz-type conditions, our convergence guarantees depend only on the geometric distribution of restricted minima across the $k$-dimensional subspaces passing through a given point in $\mathbb{R}^d$. We identify a gap parameter -- an analogue of a spectral gap for random walks -- that controls the rate at which the iterates approach the global minimum value. Finally, we argue that the same analysis yields a blind-spot robustness property: sufficiently narrow, deep dips of the loss function (small-measure regions where $\ell$ spikes downward) have limited influence on the algorithm's trajectory, since they are unlikely to be encountered by random subspace sampling. △ Less

Submitted 13 May, 2026; originally announced May 2026.

Comments: 21 pages

Engineering Mythology: A Digital-Physical Framework for Culturally-Inspired Public Art

Authors: Jnaneshwar Das, Christopher Filkins, Rajesh Moharana, Ekadashi Barik, Bishweshwar Das, David Ayers, Christopher Skiba, Rodney Staggers Jr, Mark Dill, Swig Miller, Daniel Tulberg, Patrick Smith, Seth Brink, Kyle Breen, Harish Anand, Ramon Arrowsmith

Abstract: Navagunjara Reborn: The Phoenix of Odisha was built for Burning Man 2025 as both a sculpture and an experiment-a fusion of myth, craft, and computation. This paper describes the digital-physical workflow developed for the project: a pipeline that linked digital sculpting, distributed fabrication by artisans in Odisha (India), modular structural optimization in the U.S., iterative feedback through… ▽ More Navagunjara Reborn: The Phoenix of Odisha was built for Burning Man 2025 as both a sculpture and an experiment-a fusion of myth, craft, and computation. This paper describes the digital-physical workflow developed for the project: a pipeline that linked digital sculpting, distributed fabrication by artisans in Odisha (India), modular structural optimization in the U.S., iterative feedback through photogrammetry and digital twins, and finally, one-shot full assembly at the art site in Black Rock Desert, Nevada. The desert installation tested not just materials, but also systems of collaboration: between artisans and engineers, between myth and technology, between cultural specificity and global experimentation. We share the lessons learned in design, fabrication, and deployment and offer a framework for future interdisciplinary projects at the intersection of cultural heritage, STEAM education, and public art. In retrospect, this workflow can be read as a convergence of many knowledge systems-artisan practice, structural engineering, mythic narrative, and environmental constraint-rather than as execution of a single fixed blueprint. △ Less

Submitted 29 March, 2026; originally announced March 2026.

Comments: 19 pages, 28 figures, 4 tables

ACM Class: I.3.5; I.3.8; I.4.1; J.5; J.2

GazeXPErT: An Expert Eye-tracking Dataset for Interpretable and Explainable AI in Oncologic FDG-PET/CT Scans

Authors: Joy T Wu, Daniel Beckmann, Sarah Miller, Alexander Lee, Elizabeth Theng, Stephan Altmayer, Ken Chang, David Kersting, Tomoaki Otani, Brittany Z Dashevsky, Hye Lim Park, Matteo Novello, Kip Guja, Curtis Langlotz, Ismini Lourentzou, Daniel Gruhl, Benjamin Risse, Guido A Davidzon

Abstract: [18F]FDG-PET/CT is a cornerstone imaging modality for guiding oncology therapies, yet human expert shortages necessitate more efficient diagnostic aids. While standalone AI models for automatic lesion detection exist, clinical translation remains hindered by AI explainability, reliability, and workflow integration. Meanwhile, human-computer-interaction in radiology remain limited to keyboard, mous… ▽ More [18F]FDG-PET/CT is a cornerstone imaging modality for guiding oncology therapies, yet human expert shortages necessitate more efficient diagnostic aids. While standalone AI models for automatic lesion detection exist, clinical translation remains hindered by AI explainability, reliability, and workflow integration. Meanwhile, human-computer-interaction in radiology remain limited to keyboard, mouse and voice, ignoring experts' faster, natural gaze signal. We present GazeXPErT, a 4D eye-tracking dataset with annotated expert decision windows for tumor detection and measurement on 346 dual-read FDG-PET/CTs. The dataset contributes 9,030 gaze-to-lesion trajectories derived from 3,948 minutes of 60 Hz eye-tracking data, rendered in COCO-style format. GazeXPErT captures experts' visual reasoning patterns when adjudicating suspicious lesions. It aims to facilitate development of trusted, explainable and interactive AI models through understanding expert gaze patterns. Baseline feasibility experiments suggest salient signal is extractable from routinely collected expert gaze (3D nnU-Net Dice: 0.6819 versus 0.6008 without), that gaze-trained vision transformers may aid dynamic lesion localization (74.95% predicted gaze closer to tumor), and that experts' intent may be predictable from raw gaze (Accuracy 67.53%, AUROC 0.747). △ Less

Submitted 17 August, 2026; v1 submitted 25 February, 2026; originally announced March 2026.

NeuCLIRTech: Chinese Monolingual and Cross-Language Information Retrieval Evaluation in a Challenging Domain

Authors: Dawn Lawrie, James Mayfield, Eugene Yang, Andrew Yates, Sean MacAvaney, Ronak Pradeep, Scott Miller, Paul McNamee, Luca Soldaini

Abstract: Measuring advances in retrieval requires test collections with relevance judgments that can faithfully distinguish systems. This paper presents NeuCLIRTech, an evaluation collection for cross-language retrieval over technical information. The collection consists of technical documents written natively in Chinese and those same documents machine translated into English. It includes 110 queries with… ▽ More Measuring advances in retrieval requires test collections with relevance judgments that can faithfully distinguish systems. This paper presents NeuCLIRTech, an evaluation collection for cross-language retrieval over technical information. The collection consists of technical documents written natively in Chinese and those same documents machine translated into English. It includes 110 queries with relevance judgments. The collection supports two retrieval scenarios: monolingual retrieval in Chinese, and cross-language retrieval with English as the query language. NeuCLIRTech combines the TREC NeuCLIR track topics of 2023 and 2024. The 110 queries with 35,962 document judgments provide strong statistical discriminatory power when trying to distinguish retrieval approaches. A fusion baseline of strong neural retrieval systems is included so that developers of reranking algorithms are not reliant on BM25 as their first stage retriever. The dataset and artifacts are released on Huggingface Datasets △ Less

Submitted 5 February, 2026; originally announced February 2026.

Comments: 14 pages, 6 figures

Macro-Scale Electrostatic Origami Motor

Authors: Alex S. Miller, Leo McElroy, Jeffrey H. Lang

Abstract: Foldable robots have been an active area of robotics research due to their high volume-to-mass ratio, easy packability, and shape adaptability. For locomotion, previously developed foldable robots have either embedded linear actuators in, or attached non-folding rotary motors to, their structure. Further, those actuators directly embedded in the structure of the folding medium all contributed to l… ▽ More Foldable robots have been an active area of robotics research due to their high volume-to-mass ratio, easy packability, and shape adaptability. For locomotion, previously developed foldable robots have either embedded linear actuators in, or attached non-folding rotary motors to, their structure. Further, those actuators directly embedded in the structure of the folding medium all contributed to linear or folding motion, not to continuous rotary motion. On the macro-scale there has not yet been a folding continuous rotary actuator. This paper details the development and testing of the first macro-scale origami rotary motor that can be folded flat, and then unfurled to operate. Using corona discharge for torque production, the prototype motor achieved an expansion ratio of 2.5:1, reached a top speed of 1440 rpm when driven at -29 kV, and exhibited a maximum output torque over 0.15 mN m with an active component torque density of 0.04 Nm/kg. △ Less

Submitted 29 January, 2026; originally announced January 2026.

Similarity-Sensitive Entropy under Representation Change and Inference

Authors: Joseph Samuel Miller

Abstract: Similarity-sensitive entropy measures the uncertainty of a probability law relative to a similarity kernel that encodes the distinguishability between states. We develop a measure-theoretic treatment covering both finite similarity matrices and general probability spaces, and study how the law and similarity kernel transform under measurable maps, Markov kernels (channels), and conditioning operat… ▽ More Similarity-sensitive entropy measures the uncertainty of a probability law relative to a similarity kernel that encodes the distinguishability between states. We develop a measure-theoretic treatment covering both finite similarity matrices and general probability spaces, and study how the law and similarity kernel transform under measurable maps, Markov kernels (channels), and conditioning operations. This yields deterministic and channel data-processing inequalities, so a reduction in entropy quantifies how much distinguishability is lost under representation change. We also define a conditional similarity sensitive entropy theory, give a counterexample to a recent conjecture on concavity, and identify a useful one-dimensional Laplace pullback class where concavity holds. △ Less

Submitted 27 May, 2026; v1 submitted 6 January, 2026; originally announced January 2026.

Comments: 26 pages. v2: Revised title and abstract; condensed discrete sections; added results on conditional entropy; revised theorem statements

amc: The Automated Mission Classifier for Telescope Bibliographies

Authors: John F. Wu, Joshua E. G. Peek, Sophie J. Miller, Jenny Novacescu, Achu J. Usha, Christopher A. Wilkinson

Abstract: Telescope bibliographies record the pulse of astronomy research by capturing publication statistics and citation metrics for telescope facilities. Robust and scalable bibliographies ensure that we can measure the scientific impact of our facilities and archives. However, the growing rate of publications threatens to outpace our ability to manually label astronomical literature. We therefore presen… ▽ More Telescope bibliographies record the pulse of astronomy research by capturing publication statistics and citation metrics for telescope facilities. Robust and scalable bibliographies ensure that we can measure the scientific impact of our facilities and archives. However, the growing rate of publications threatens to outpace our ability to manually label astronomical literature. We therefore present the Automated Mission Classifier (amc), a tool that uses large language models (LLMs) to identify and categorize telescope references by processing large quantities of paper text. A modified version of amc performs well on the TRACS Kaggle challenge, achieving a macro $F_1$ score of 0.84 on the held-out test set. amc is valuable for other telescopes beyond TRACS; we developed the initial software for identifying papers that featured scientific results by NASA missions. Additionally, we investigate how amc can also be used to interrogate historical datasets and surface potential label errors. Our work demonstrates that LLM-based applications offer powerful and scalable assistance for library sciences. △ Less

Submitted 11 December, 2025; originally announced December 2025.

Comments: Accepted to IJCNLP-AACL WASP 2025 workshop. Code available at: https://github.com/jwuphysics/automated-mission-classifier

NeuCLIRBench: A Modern Evaluation Collection for Monolingual, Cross-Language, and Multilingual Information Retrieval

Authors: Dawn Lawrie, James Mayfield, Eugene Yang, Andrew Yates, Sean MacAvaney, Ronak Pradeep, Scott Miller, Paul McNamee, Luca Soldani

Abstract: To measure advances in retrieval, test collections with relevance judgments that can faithfully distinguish systems are required. This paper presents NeuCLIRBench, an evaluation collection for cross-language and multilingual retrieval. The collection consists of documents written natively in Chinese, Persian, and Russian, as well as those same documents machine translated into English. The collect… ▽ More To measure advances in retrieval, test collections with relevance judgments that can faithfully distinguish systems are required. This paper presents NeuCLIRBench, an evaluation collection for cross-language and multilingual retrieval. The collection consists of documents written natively in Chinese, Persian, and Russian, as well as those same documents machine translated into English. The collection supports several retrieval scenarios including: monolingual retrieval in English, Chinese, Persian, or Russian; cross-language retrieval with English as the query language and one of the other three languages as the document language; and multilingual retrieval, again with English as the query language and relevant documents in all three languages. NeuCLIRBench combines the TREC NeuCLIR track topics of 2022, 2023, and 2024. The 250,128 judgments across approximately 150 queries for the monolingual and cross-language tasks and 100 queries for multilingual retrieval provide strong statistical discriminatory power to distinguish retrieval approaches. A fusion baseline of strong neural retrieval systems is included with the collection so that developers of reranking algorithms are no longer reliant on BM25 as their first-stage retriever. NeuCLIRBench is publicly available. △ Less

Submitted 18 November, 2025; originally announced November 2025.

Comments: 14 pages, 1 figure

Beyond Ranked Lists: The SARAL Framework for Cross-Lingual Document Set Retrieval

Authors: Shantanu Agarwal, Joel Barry, Elizabeth Boschee, Scott Miller

Abstract: Machine Translation for English Retrieval of Information in Any Language (MATERIAL) is an IARPA initiative targeted to advance the state of cross-lingual information retrieval (CLIR). This report provides a detailed description of Information Sciences Institute's (ISI's) Summarization and domain-Adaptive Retrieval Across Language's (SARAL's) effort for MATERIAL. Specifically, we outline our team's… ▽ More Machine Translation for English Retrieval of Information in Any Language (MATERIAL) is an IARPA initiative targeted to advance the state of cross-lingual information retrieval (CLIR). This report provides a detailed description of Information Sciences Institute's (ISI's) Summarization and domain-Adaptive Retrieval Across Language's (SARAL's) effort for MATERIAL. Specifically, we outline our team's novel approach to handle CLIR with emphasis in developing an approach amenable to retrieve a query-relevant document \textit{set}, and not just a ranked document-list. In MATERIAL's Phase-3 evaluations, SARAL exceeded the performance of other teams in five out of six evaluation conditions spanning three different languages (Farsi, Kazakh, and Georgian). △ Less

Submitted 5 November, 2025; originally announced November 2025.

Cross-Genre Authorship Attribution via LLM-Based Retrieve-and-Rerank

Authors: Shantanu Agarwal, Joel Barry, Steven Fincke, Scott Miller

Abstract: Authorship attribution (AA) is the task of identifying the most likely author of a query document from a predefined set of candidate authors. We introduce a two-stage retrieve-and-rerank framework that finetunes LLMs for cross-genre AA. Unlike the field of information retrieval (IR), where retrieve-and-rerank is a de facto strategy, cross-genre AA systems must avoid relying on topical cues and ins… ▽ More Authorship attribution (AA) is the task of identifying the most likely author of a query document from a predefined set of candidate authors. We introduce a two-stage retrieve-and-rerank framework that finetunes LLMs for cross-genre AA. Unlike the field of information retrieval (IR), where retrieve-and-rerank is a de facto strategy, cross-genre AA systems must avoid relying on topical cues and instead learn to identify author-specific linguistic patterns that are independent of the text's subject matter (genre/domain/topic). Consequently, for the reranker, we demonstrate that training strategies commonly used in IR are fundamentally misaligned with cross-genre AA, leading to suboptimal behavior. To address this, we introduce a targeted data curation strategy that enables the reranker to effectively learn author-discriminative signals. Using our LLM-based retrieve-and-rerank pipeline, we achieve substantial gains of 22.3 and 34.4 absolute Success@8 points over the previous state-of-the-art on HIATUS's challenging HRS1 and HRS2 cross-genre AA benchmarks. △ Less

Submitted 19 October, 2025; originally announced October 2025.

Function Spaces Without Kernels: Learning Compact Hilbert Space Representations

Authors: Su Ann Low, Quentin Rommel, Kevin S. Miller, Adam J. Thorpe, Ufuk Topcu

Abstract: Function encoders are a recent technique that learn neural network basis functions to form compact, adaptive representations of Hilbert spaces of functions. We show that function encoders provide a principled connection to feature learning and kernel methods by defining a kernel through an inner product of the learned feature map. This kernel-theoretic perspective explains their ability to scale i… ▽ More Function encoders are a recent technique that learn neural network basis functions to form compact, adaptive representations of Hilbert spaces of functions. We show that function encoders provide a principled connection to feature learning and kernel methods by defining a kernel through an inner product of the learned feature map. This kernel-theoretic perspective explains their ability to scale independently of dataset size while adapting to the intrinsic structure of data, and it enables kernel-style analysis of neural models. Building on this foundation, we develop two training algorithms that learn compact bases: a progressive training approach that constructively grows bases, and a train-then-prune approach that offers a computationally efficient alternative after training. Both approaches use principles from PCA to reveal the intrinsic dimension of the learned space. In parallel, we derive finite-sample generalization bounds using Rademacher complexity and PAC-Bayes techniques, providing inference time guarantees. We validate our approach on a polynomial benchmark with a known intrinsic dimension, and on nonlinear dynamical systems including a Van der Pol oscillator and a two-body orbital model, demonstrating that the same accuracy can be achieved with substantially fewer basis functions. This work suggests a path toward neural predictors with kernel-level guarantees, enabling adaptable models that are both efficient and principled at scale. △ Less

Submitted 24 September, 2025; originally announced September 2025.

Comments: Submitted to ICLR 2026

Proof of Hiding Conjecture in Gaussian Boson Sampling

Authors: Laura Shou, Sarah H. Miller, Victor Galitski

Abstract: Gaussian boson sampling (GBS) is a promising protocol for demonstrating quantum computational advantage. One of the key steps for proving classical hardness of GBS is the so-called ``hiding conjecture'', which asserts that one can ``hide'' a complex Gaussian matrix as a submatrix of the outer product of Haar unitary submatrices in total variation distance. In this paper, we prove the hiding conjec… ▽ More Gaussian boson sampling (GBS) is a promising protocol for demonstrating quantum computational advantage. One of the key steps for proving classical hardness of GBS is the so-called ``hiding conjecture'', which asserts that one can ``hide'' a complex Gaussian matrix as a submatrix of the outer product of Haar unitary submatrices in total variation distance. In this paper, we prove the hiding conjecture for input states with the maximal number of squeezed states, which is a setup that has recently been realized experimentally [Madsen et al., Nature 606, 75 (2022)]. In this setting, the hiding conjecture states that a $o(\sqrt{M})\times o(\sqrt{M})$ submatrix of an $M\times M$ circular orthogonal ensemble (COE) random matrix can be well-approximated by a complex Gaussian matrix in total variation distance as $M\to\infty$. This is the first rigorous proof of the hiding property for GBS in the experimentally relevant regime, and puts the argument for hardness of classically simulating GBS with a maximal number of squeezed states on a comparable level to that of the conventional boson sampling of [Aaronson and Arkhipov, Theory Comput. 9, 143 (2013)]. △ Less

Submitted 1 September, 2025; v1 submitted 1 August, 2025; originally announced August 2025.

Comments: 22 pages, 4 figures

Benchmarking a Tunable Quantum Neural Network on Trapped-Ion and Superconducting Hardware

Authors: Djamil Lakhdar-Hamina, Xingxin Liu, Richard Barney, Sarah H. Miller, Alaina M. Green, Norbert M. Linke, Victor Galitski

Abstract: We implement a quantum generalization of a neural network on trapped-ion and IBM superconducting quantum computers to classify MNIST images, a common benchmark in computer vision. The network feedforward involves qubit rotations whose angles depend on the results of measurements in the previous layer. The network is trained via simulation, but inference is performed experimentally on quantum hardw… ▽ More We implement a quantum generalization of a neural network on trapped-ion and IBM superconducting quantum computers to classify MNIST images, a common benchmark in computer vision. The network feedforward involves qubit rotations whose angles depend on the results of measurements in the previous layer. The network is trained via simulation, but inference is performed experimentally on quantum hardware. The classical-to-quantum correspondence is controlled by an interpolation parameter, $a$, which is zero in the classical limit. Increasing $a$ introduces quantum uncertainty into the measurements, which is shown to improve network performance at moderate values of the interpolation parameter. We then focus on particular images that fail to be classified by a classical neural network but are detected correctly in the quantum network. For such borderline cases, we observe strong deviations from the simulated behavior. We attribute this to physical noise, which causes the output to fluctuate between nearby minima of the classification energy landscape. Such strong sensitivity to physical noise is absent for clear images. We further benchmark physical noise by inserting additional single-qubit and two-qubit gate pairs into the neural network circuits. Our work provides a springboard toward more complex quantum neural networks on current devices: while the approach is rooted in standard classical machine learning, scaling up such networks may prove classically non-simulable and could offer a route to near-term quantum advantage. △ Less

Submitted 5 August, 2025; v1 submitted 28 July, 2025; originally announced July 2025.

Comments: 6 pages, 3 figures

TextSAM-EUS: Text Prompt Learning for SAM to Accurately Segment Pancreatic Tumor in Endoscopic Ultrasound

Authors: Pascal Spiegler, Taha Koleilat, Arash Harirpoush, Corey S. Miller, Hassan Rivaz, Marta Kersten-Oertel, Yiming Xiao

Abstract: Pancreatic cancer carries a poor prognosis and relies on endoscopic ultrasound (EUS) for targeted biopsy and radiotherapy. However, the speckle noise, low contrast, and unintuitive appearance of EUS make segmentation of pancreatic tumors with fully supervised deep learning (DL) models both error-prone and dependent on large, expert-curated annotation datasets. To address these challenges, we prese… ▽ More Pancreatic cancer carries a poor prognosis and relies on endoscopic ultrasound (EUS) for targeted biopsy and radiotherapy. However, the speckle noise, low contrast, and unintuitive appearance of EUS make segmentation of pancreatic tumors with fully supervised deep learning (DL) models both error-prone and dependent on large, expert-curated annotation datasets. To address these challenges, we present TextSAM-EUS, a novel, lightweight, text-driven adaptation of the Segment Anything Model (SAM) that requires no manual geometric prompts at inference. Our approach leverages text prompt learning (context optimization) through the BiomedCLIP text encoder in conjunction with a LoRA-based adaptation of SAM's architecture to enable automatic pancreatic tumor segmentation in EUS, tuning only 0.86% of the total parameters. On the public Endoscopic Ultrasound Database of the Pancreas, TextSAM-EUS with automatic prompts attains 82.69% Dice and 85.28% normalized surface distance (NSD), and with manual geometric prompts reaches 83.10% Dice and 85.70% NSD, outperforming both existing state-of-the-art (SOTA) supervised DL models and foundation models (e.g., SAM and its variants). As the first attempt to incorporate prompt learning in SAM-based medical image segmentation, TextSAM-EUS offers a practical option for efficient and robust automatic EUS segmentation. Code is available at https://github.com/HealthX-Lab/TextSAM-EUS . △ Less

Submitted 30 July, 2025; v1 submitted 24 July, 2025; originally announced July 2025.

Comments: Accepted to ICCV 2025 Workshop CVAMD

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones

Authors: Daking Rai, Samuel Miller, Kevin Moran, Ziyu Yao

Abstract: Despite remarkable advances in coding capabilities, language models (LMs) still struggle with simple syntactic tasks such as generating balanced parentheses. In this study, we investigate the underlying mechanisms behind the persistence of these errors across LMs of varying sizes (124M-7B) to both understand and mitigate the errors. Our study reveals that LMs rely on a number of components (attent… ▽ More Despite remarkable advances in coding capabilities, language models (LMs) still struggle with simple syntactic tasks such as generating balanced parentheses. In this study, we investigate the underlying mechanisms behind the persistence of these errors across LMs of varying sizes (124M-7B) to both understand and mitigate the errors. Our study reveals that LMs rely on a number of components (attention heads and FF neurons) that independently make their own predictions. While some components reliably promote correct answers across a generalized range of inputs (i.e., implementing "sound mechanisms''), others are less reliable and introduce noise by promoting incorrect tokens (i.e., implementing "faulty mechanisms''). Errors occur when the faulty mechanisms overshadow the sound ones and dominantly affect the predictions. Motivated by this insight, we introduce RASteer, a steering method to systematically identify and increase the contribution of reliable components for improving model performance. RASteer substantially improves performance on balanced parentheses tasks, boosting accuracy of some models from $0$% to around $100$% without impairing the models' general coding ability. We further demonstrate its broader applicability in arithmetic reasoning tasks, achieving performance gains of up to around $20$%. △ Less

Submitted 8 June, 2026; v1 submitted 30 June, 2025; originally announced July 2025.

Comments: 23 pages, 10 figures, accepted for NeurIPS 2025

ACM Class: I.2.7

Adaptive AI decision interface for autonomous electronic material discovery

Authors: Yahao Dai, Henry Chan, Aikaterini Vriza, Fredrick Kim, Yunfei Wang, Wei Liu, Naisong Shan, Jing Xu, Max Weires, Yukun Wu, Zhiqiang Cao, C. Suzanne Miller, Ralu Divan, Xiaodan Gu, Chenhui Zhu, Sihong Wang, Jie Xu

Abstract: AI-powered autonomous experimentation (AI/AE) can accelerate materials discovery but its effectiveness for electronic materials is hindered by data scarcity from lengthy and complex design-fabricate-test-analyze cycles. Unlike experienced human scientists, even advanced AI algorithms in AI/AE lack the adaptability to make informative real-time decisions with limited datasets. Here, we address this… ▽ More AI-powered autonomous experimentation (AI/AE) can accelerate materials discovery but its effectiveness for electronic materials is hindered by data scarcity from lengthy and complex design-fabricate-test-analyze cycles. Unlike experienced human scientists, even advanced AI algorithms in AI/AE lack the adaptability to make informative real-time decisions with limited datasets. Here, we address this challenge by developing and implementing an AI decision interface on our AI/AE system. The central element of the interface is an AI advisor that performs real-time progress monitoring, data analysis, and interactive human-AI collaboration for actively adapting to experiments in different stages and types. We applied this platform to an emerging type of electronic materials-mixed ion-electron conducting polymers (MIECPs) -- to engineer and study the relationships between multiscale morphology and properties. Using organic electrochemical transistors (OECT) as the testing-bed device for evaluating the mixed-conducting figure-of-merit -- the product of charge-carrier mobility and the volumetric capacitance (μC*), our adaptive AI/AE platform achieved a 150% increase in μC* compared to the commonly used spin-coating method, reaching 1,275 F cm-1 V-1 s-1 in just 64 autonomous experimental trials. A study of 10 statistically selected samples identifies two key structural factors for achieving higher volumetric capacitance: larger crystalline lamellar spacing and higher specific surface area, while also uncovering a new polymer polymorph in this material. △ Less

Submitted 17 April, 2025; originally announced April 2025.

MURR: Model Updating with Regularized Replay for Searching a Document Stream

Authors: Eugene Yang, Nicola Tonellotto, Dawn Lawrie, Sean MacAvaney, James Mayfield, Douglas W. Oard, Scott Miller

Abstract: The Internet produces a continuous stream of new documents and user-generated queries. These naturally change over time based on events in the world and the evolution of language. Neural retrieval models that were trained once on a fixed set of query-document pairs will quickly start misrepresenting newly-created content and queries, leading to less effective retrieval. Traditional statistical spa… ▽ More The Internet produces a continuous stream of new documents and user-generated queries. These naturally change over time based on events in the world and the evolution of language. Neural retrieval models that were trained once on a fixed set of query-document pairs will quickly start misrepresenting newly-created content and queries, leading to less effective retrieval. Traditional statistical sparse retrieval can update collection statistics to reflect these changes in the use of language in documents and queries. In contrast, continued fine-tuning of the language model underlying neural retrieval approaches such as DPR and ColBERT creates incompatibility with previously-encoded documents. Re-encoding and re-indexing all previously-processed documents can be costly. In this work, we explore updating a neural dual encoder retrieval model without reprocessing past documents in the stream. We propose MURR, a model updating strategy with regularized replay, to ensure the model can still faithfully search existing documents without reprocessing, while continuing to update the model for the latest topics. In our simulated streaming environments, we show that fine-tuning models using MURR leads to more effective and more consistent retrieval results than other strategies as the stream of documents and queries progresses. △ Less

Submitted 14 April, 2025; originally announced April 2025.

Comments: Published at ECIR 2025. 16 pages, 4 figures

AI Judges in Design: Statistical Perspectives on Achieving Human Expert Equivalence With Vision-Language Models

Authors: Kristen M. Edwards, Farnaz Tehranchi, Scarlett R. Miller, Faez Ahmed

Abstract: The subjective evaluation of early stage engineering designs, such as conceptual sketches, traditionally relies on human experts. However, expert evaluations are time-consuming, expensive, and sometimes inconsistent. Recent advances in vision-language models (VLMs) offer the potential to automate design assessments, but it is crucial to ensure that these AI ``judges'' perform on par with human exp… ▽ More The subjective evaluation of early stage engineering designs, such as conceptual sketches, traditionally relies on human experts. However, expert evaluations are time-consuming, expensive, and sometimes inconsistent. Recent advances in vision-language models (VLMs) offer the potential to automate design assessments, but it is crucial to ensure that these AI ``judges'' perform on par with human experts. However, no existing framework assesses expert equivalence. This paper introduces a rigorous statistical framework to determine whether an AI judge's ratings match those of human experts. We apply this framework in a case study evaluating four VLM-based judges on key design metrics (uniqueness, creativity, usefulness, and drawing quality). These AI judges employ various in-context learning (ICL) techniques, including uni- vs. multimodal prompts and inference-time reasoning. The same statistical framework is used to assess three trained novices for expert-equivalence. Results show that the top-performing AI judge, using text- and image-based ICL with reasoning, achieves expert-level agreement for uniqueness and drawing quality and outperforms or matches trained novices across all metrics. In 6/6 runs for both uniqueness and creativity, and 5/6 runs for both drawing quality and usefulness, its agreement with experts meets or exceeds that of the majority of trained novices. These findings suggest that reasoning-supported VLM models can achieve human-expert equivalence in design evaluation. This has implications for scaling design evaluation in education and practice, and provides a general statistical framework for validating AI judges in other domains requiring subjective content evaluation. △ Less

Submitted 1 April, 2025; originally announced April 2025.

Comments: 21 pages, 8 tables, 6 figures, 8 tables in the appendix

Mechanistic Understanding of Language Models in Syntactic Code Completion

Authors: Samuel Miller, Daking Rai, Ziyu Yao

Abstract: Recently, language models (LMs) have shown impressive proficiency in code generation tasks, especially when fine-tuned on code-specific datasets, commonly known as Code LMs. However, our understanding of the internal decision-making processes of Code LMs, such as how they use their (syntactic or semantic) knowledge, remains limited, which could lead to unintended harm as they are increasingly used… ▽ More Recently, language models (LMs) have shown impressive proficiency in code generation tasks, especially when fine-tuned on code-specific datasets, commonly known as Code LMs. However, our understanding of the internal decision-making processes of Code LMs, such as how they use their (syntactic or semantic) knowledge, remains limited, which could lead to unintended harm as they are increasingly used in real life. This motivates us to conduct one of the first Mechanistic Interpretability works to understand how Code LMs perform a syntactic completion task, specifically the closing parenthesis task, on the CodeLlama-7b model (Roziere et al. 2023). Our findings reveal that the model requires middle-later layers until it can confidently predict the correct label for the closing parenthesis task. Additionally, we identify that while both multi-head attention (MHA) and feed-forward (FF) sub-layers play essential roles, MHA is particularly crucial. Furthermore, we also discover attention heads that keep track of the number of already closed parentheses precisely but may or may not promote a correct number of closing parentheses that are still missing, leading to a positive or negative impact on the model's performance. △ Less

Submitted 20 February, 2025; originally announced February 2025.

Comments: 10 pages, 4 figures, accepted to the AAAI 2025 Workshop on Towards Knowledgeable Foundation Models

ACM Class: I.2.7

Growing Neural Networks: Dynamic Evolution through Gradient Descent

Authors: Anil Radhakrishnan, John F. Lindner, Scott T. Miller, Sudeshna Sinha, William L. Ditto

Abstract: In contrast to conventional artificial neural networks, which are structurally static, we present two approaches for evolving small networks into larger ones during training. The first method employs an auxiliary weight that directly controls network size, while the second uses a controller-generated mask to modulate neuron participation. Both approaches optimize network size through the same grad… ▽ More In contrast to conventional artificial neural networks, which are structurally static, we present two approaches for evolving small networks into larger ones during training. The first method employs an auxiliary weight that directly controls network size, while the second uses a controller-generated mask to modulate neuron participation. Both approaches optimize network size through the same gradient-descent algorithm that updates the network's weights and biases. We evaluate these growing networks on nonlinear regression and classification tasks, where they consistently outperform static networks of equivalent final size. We then explore the hyperparameter space of these networks to find associated scaling relations relative to their static counterparts. Our results suggest that starting small and growing naturally may be preferable to simply starting large, particularly as neural networks continue to grow in size and energy consumption. △ Less

Submitted 25 July, 2025; v1 submitted 29 January, 2025; originally announced January 2025.

Comments: 11 pages, 9 figures; adding scaling results, revised introduction, abstract, and title

Journal ref: Proceedings of the Royal Society A, volume 481, issue 2318, pages 20250222(1-15) (16 July 2025)

AgreeMate: Teaching LLMs to Haggle

Authors: Ainesh Chatterjee, Samuel Miller, Nithin Parepally

Abstract: We introduce AgreeMate, a framework for training Large Language Models (LLMs) to perform strategic price negotiations through natural language. We apply recent advances to a negotiation setting where two agents (i.e. buyer or seller) use natural language to bargain on goods using coarse actions. Specifically, we present the performance of Large Language Models when used as agents within a decouple… ▽ More We introduce AgreeMate, a framework for training Large Language Models (LLMs) to perform strategic price negotiations through natural language. We apply recent advances to a negotiation setting where two agents (i.e. buyer or seller) use natural language to bargain on goods using coarse actions. Specifically, we present the performance of Large Language Models when used as agents within a decoupled (modular) bargaining architecture. We demonstrate that using prompt engineering, fine-tuning, and chain-of-thought prompting enhances model performance, as defined by novel metrics. We use attention probing to show model attention to semantic relationships between tokens during negotiations. △ Less

Submitted 24 December, 2024; originally announced December 2024.

Comments: 15 pages, 22 figures, 6 tables

A User Study Method on Healthy Participants for Assessing an Assistive Wearable Robot Utilising EMG Sensing

Authors: Cem Suulker, Alexander Greenway, Sophie Skach, Ildar Farkhatdinov, Stuart Charles Miller, Kaspar Althoefer

Abstract: Hand-wearable robots, specifically exoskeletons, are designed to aid hands in daily activities, playing a crucial role in post-stroke rehabilitation and assisting the elderly. Our contribution to this field is a textile robotic glove with integrated actuators. These actuators, powered by pneumatic pressure, guide the user's hand to a desired position. Crafted from textile materials, our soft robot… ▽ More Hand-wearable robots, specifically exoskeletons, are designed to aid hands in daily activities, playing a crucial role in post-stroke rehabilitation and assisting the elderly. Our contribution to this field is a textile robotic glove with integrated actuators. These actuators, powered by pneumatic pressure, guide the user's hand to a desired position. Crafted from textile materials, our soft robotic glove prioritizes safety, lightweight construction, and user comfort. Utilizing the ruffles technique, integrated actuators guarantee high performance in blocking force and bending effectiveness. Here, we present a participant study confirming the effectiveness of our robotic device on a healthy participant group, exploiting EMG sensing. △ Less

Submitted 31 July, 2024; originally announced August 2024.

Comments: 3 pages, 4 figures, conference. arXiv admin note: text overlap with arXiv:2305.17720

Journal ref: Assistive Systems: Lab to Patient Care, ICRA2024 Workshop

WorkBench: a Benchmark Dataset for Agents in a Realistic Workplace Setting

Authors: Olly Styles, Sam Miller, Patricio Cerda-Mardini, Tanaya Guha, Victor Sanchez, Bertie Vidgen

Abstract: We introduce WorkBench: a benchmark dataset for evaluating agents' ability to execute tasks in a workplace setting. WorkBench contains a sandbox environment with five databases, 26 tools, and 690 tasks. These tasks represent common business activities, such as sending emails and scheduling meetings. The tasks in WorkBench are challenging as they require planning, tool selection, and often multiple… ▽ More We introduce WorkBench: a benchmark dataset for evaluating agents' ability to execute tasks in a workplace setting. WorkBench contains a sandbox environment with five databases, 26 tools, and 690 tasks. These tasks represent common business activities, such as sending emails and scheduling meetings. The tasks in WorkBench are challenging as they require planning, tool selection, and often multiple actions. If a task has been successfully executed, one (or more) of the database values may change. The correct outcome for each task is unique and unambiguous, which allows for robust, automated evaluation. We call this key contribution outcome-centric evaluation. We evaluate five existing ReAct agents on WorkBench, finding they successfully complete as few as 3% of tasks (Llama2-70B), and just 43% for the best-performing (GPT-4). We further find that agents' errors can result in the wrong action being taken, such as an email being sent to the wrong person. WorkBench reveals weaknesses in agents' ability to undertake common business activities, raising questions about their use in high-stakes workplace settings. WorkBench is publicly available as a free resource at https://github.com/olly-styles/WorkBench. △ Less

Submitted 3 August, 2024; v1 submitted 1 May, 2024; originally announced May 2024.

Active Learning of Dynamics Using Prior Domain Knowledge in the Sampling Process

Authors: Kevin S. Miller, Adam J. Thorpe, Ufuk Topcu

Abstract: We present an active learning algorithm for learning dynamics that leverages side information by explicitly incorporating prior domain knowledge into the sampling process. Our proposed algorithm guides the exploration toward regions that demonstrate high empirical discrepancy between the observed data and an imperfect prior model of the dynamics derived from side information. Through numerical exp… ▽ More We present an active learning algorithm for learning dynamics that leverages side information by explicitly incorporating prior domain knowledge into the sampling process. Our proposed algorithm guides the exploration toward regions that demonstrate high empirical discrepancy between the observed data and an imperfect prior model of the dynamics derived from side information. Through numerical experiments, we demonstrate that this strategy explores regions of high discrepancy and accelerates learning while simultaneously reducing model uncertainty. We rigorously prove that our active learning algorithm yields a consistent estimate of the underlying dynamics by providing an explicit rate of convergence for the maximum predictive variance. We demonstrate the efficacy of our approach on an under-actuated pendulum system and on the half-cheetah MuJoCo environment. △ Less

Submitted 25 March, 2024; originally announced March 2024.

PureConnect: A Localized Social Media System to Increase Awareness and Connectedness in Environmental Justice Communities

Authors: Omar Hammad, Md Rezwanur Rahman, Gopala Krishna Vasanth Kanugo, Nicholas Clements, Shelly Miller, Shivakant Mishra, Esther Sullivan

Abstract: Frequent disruptions like highway constructions are common now-a-days, often impacting environmental justice communities (communities with low socio-economic status with disproportionately high and adverse human health and environmental effects) that live nearby. Based on our interactions via focus groups with the members of four environmental justice communities impacted by a major highway constr… ▽ More Frequent disruptions like highway constructions are common now-a-days, often impacting environmental justice communities (communities with low socio-economic status with disproportionately high and adverse human health and environmental effects) that live nearby. Based on our interactions via focus groups with the members of four environmental justice communities impacted by a major highway construction, a common concern is a sense of uncertainty about project activities and loss of social connectedness, leading to increased stress, depression, anxiety and diminished well-being. This paper addresses this concern by developing a localized social media system called PureConnect with a goal to raise the level of awareness about the project and increase social connectedness among the community members. PureConnect has been designed using active engagement with four environmental justice communities affected by a major highway construction. It has been deployed in the real world among the members of the four environmental justice communities, and a detailed analysis of the data collected from this deployment as well as surveys show that PureConnect is potentially useful in improving community members' well-being and the members appreciate the functionalities it provides. △ Less

Submitted 20 March, 2024; originally announced March 2024.

Comments: Submitted in COMPSAC 2024

Copilot Evaluation Harness: Evaluating LLM-Guided Software Programming

Authors: Anisha Agarwal, Aaron Chan, Shubham Chandel, Jinu Jang, Shaun Miller, Roshanak Zilouchian Moghaddam, Yevhen Mohylevskyy, Neel Sundaresan, Michele Tufano

Abstract: The integration of Large Language Models (LLMs) into Development Environments (IDEs) has become a focal point in modern software development. LLMs such as OpenAI GPT-3.5/4 and Code Llama offer the potential to significantly augment developer productivity by serving as intelligent, chat-driven programming assistants. However, utilizing LLMs out of the box is unlikely to be optimal for any given sce… ▽ More The integration of Large Language Models (LLMs) into Development Environments (IDEs) has become a focal point in modern software development. LLMs such as OpenAI GPT-3.5/4 and Code Llama offer the potential to significantly augment developer productivity by serving as intelligent, chat-driven programming assistants. However, utilizing LLMs out of the box is unlikely to be optimal for any given scenario. Rather, each system requires the LLM to be honed to its set of heuristics to ensure the best performance. In this paper, we introduce the Copilot evaluation harness: a set of data and tools for evaluating LLM-guided IDE interactions, covering various programming scenarios and languages. We propose our metrics as a more robust and information-dense evaluation than previous state of the art evaluation systems. We design and compute both static and execution based success metrics for scenarios encompassing a wide range of developer tasks, including code generation from natural language (generate), documentation generation from code (doc), test case generation (test), bug-fixing (fix), and workspace understanding and query resolution (workspace). These success metrics are designed to evaluate the performance of LLMs within a given IDE and its respective parameter space. Our learnings from evaluating three common LLMs using these metrics can inform the development and validation of future scenarios in LLM guided IDEs. △ Less

Submitted 21 February, 2024; originally announced February 2024.

PureNav: A Personalized Navigation Service for Environmental Justice Communities Impacted by Planned Disruptions

Authors: Omar Hammad, Md Rezwanur Rahman, Nicholas Clements, Shivakant Mishra, Shelly Miller, Esther Sullivan

Abstract: Planned disruptions such as highway constructions are commonplace nowadays and the communities living near these disruptions generally tend to be environmental justice communities -- low socioeconomic status with disproportionately high and adverse human health and environmental effects. A major concern is that such activities negatively impact people's well-being by disrupting their daily commute… ▽ More Planned disruptions such as highway constructions are commonplace nowadays and the communities living near these disruptions generally tend to be environmental justice communities -- low socioeconomic status with disproportionately high and adverse human health and environmental effects. A major concern is that such activities negatively impact people's well-being by disrupting their daily commutes via frequent road closures and increased dust and air pollution. This paper addresses this concern by developing a personalized navigation service called PureNav to mitigate the negative impacts of disruptions in daily commutes on people's well-being. PureNav has been designed using active engagement with four environmental justice communities affected by major highway construction. It has been deployed in the real world among the members of the four communities, and a detailed analysis of the data collected from this deployment as well as surveys show that PureNav is potentially useful in improving people's well-being. The paper describes the design, implementation, and evaluation of PureNav, and offers suggestions for further improving its efficacy. △ Less

Submitted 16 February, 2024; originally announced February 2024.

Comments: Accepted for publication in the proceedings of the 2023 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)

Translate-Distill: Learning Cross-Language Dense Retrieval by Translation and Distillation

Authors: Eugene Yang, Dawn Lawrie, James Mayfield, Douglas W. Oard, Scott Miller

Abstract: Prior work on English monolingual retrieval has shown that a cross-encoder trained using a large number of relevance judgments for query-document pairs can be used as a teacher to train more efficient, but similarly effective, dual-encoder student models. Applying a similar knowledge distillation approach to training an efficient dual-encoder model for Cross-Language Information Retrieval (CLIR),… ▽ More Prior work on English monolingual retrieval has shown that a cross-encoder trained using a large number of relevance judgments for query-document pairs can be used as a teacher to train more efficient, but similarly effective, dual-encoder student models. Applying a similar knowledge distillation approach to training an efficient dual-encoder model for Cross-Language Information Retrieval (CLIR), where queries and documents are in different languages, is challenging due to the lack of a sufficiently large training collection when the query and document languages differ. The state of the art for CLIR thus relies on translating queries, documents, or both from the large English MS MARCO training set, an approach called Translate-Train. This paper proposes an alternative, Translate-Distill, in which knowledge distillation from either a monolingual cross-encoder or a CLIR cross-encoder is used to train a dual-encoder CLIR student model. This richer design space enables the teacher model to perform inference in an optimized setting, while training the student model directly for CLIR. Trained models and artifacts are publicly available on Huggingface. △ Less

Submitted 9 January, 2024; originally announced January 2024.

Comments: 17 pages, 1 figure, accepted at ECIR 2024

ASL Champ!: A Virtual Reality Game with Deep-Learning Driven Sign Recognition

Authors: Md Shahinur Alam, Jason Lamberton, Jianye Wang, Carly Leannah, Sarah Miller, Joseph Palagano, Myles de Bastion, Heather L. Smith, Melissa Malzkuhn, Lorna C. Quandt

Abstract: We developed an American Sign Language (ASL) learning platform in a Virtual Reality (VR) environment to facilitate immersive interaction and real-time feedback for ASL learners. We describe the first game to use an interactive teaching style in which users learn from a fluent signing avatar and the first implementation of ASL sign recognition using deep learning within the VR environment. Advanced… ▽ More We developed an American Sign Language (ASL) learning platform in a Virtual Reality (VR) environment to facilitate immersive interaction and real-time feedback for ASL learners. We describe the first game to use an interactive teaching style in which users learn from a fluent signing avatar and the first implementation of ASL sign recognition using deep learning within the VR environment. Advanced motion-capture technology powers an expressive ASL teaching avatar within an immersive three-dimensional environment. The teacher demonstrates an ASL sign for an object, prompting the user to copy the sign. Upon the user's signing, a third-party plugin executes the sign recognition process alongside a deep learning model. Depending on the accuracy of a user's sign production, the avatar repeats the sign or introduces a new one. We gathered a 3D VR ASL dataset from fifteen diverse participants to power the sign recognition model. The proposed deep learning model's training, validation, and test accuracy are 90.12%, 89.37%, and 86.66%, respectively. The functional prototype can teach sign language vocabulary and be successfully adapted as an interactive ASL learning platform in VR. △ Less

Submitted 30 December, 2023; originally announced January 2024.

Comments: 36 pages, 9 figures

Minimal covers in the Weihrauch degrees

Authors: Steffen Lempp, Joseph S. Miller, Arno Pauly, Mariya I. Soskova, Manlio Valenti

Abstract: In this paper, we study the existence of minimal covers and strong minimal covers in the Weihrauch degrees. We characterize when a problem $f$ is a minimal cover or strong minimal cover of a problem $h$. We show that strong minimal covers only exist in the cone below $\mathsf{id}$ and that the Weihrauch lattice above $\mathsf{id}$ is dense. From this, we conclude that the degree of $\mathsf{id}$ i… ▽ More In this paper, we study the existence of minimal covers and strong minimal covers in the Weihrauch degrees. We characterize when a problem $f$ is a minimal cover or strong minimal cover of a problem $h$. We show that strong minimal covers only exist in the cone below $\mathsf{id}$ and that the Weihrauch lattice above $\mathsf{id}$ is dense. From this, we conclude that the degree of $\mathsf{id}$ is first-order definable in the Weihrauch degrees and that the first-order theory of the Weihrauch degrees is computably isomorphic to third-order arithmetic. △ Less

Submitted 21 November, 2023; originally announced November 2023.

MSC Class: 03D30 03D78

Journal ref: Proceedings of the American Mathematical Society 152 (2024), no. 11, 4893--4901

Towards Exascale Computation for Turbomachinery Flows

Authors: Yuhang Fu, Weiqi Shen, Jiahuan Cui, Yao Zheng, Guangwen Yang, Zhao Liu, Jifa Zhang, Tingwei Ji, Fangfang Xie, Xiaojing Lv, Hanyue Liu, Xu Liu, Xiyang Liu, Xiaoyu Song, Guocheng Tao, Yan Yan, Paul Tucker, Steven A. E. Miller, Shirui Luo, Seid Koric, Weimin Zheng

Abstract: A state-of-the-art large eddy simulation code has been developed to solve compressible flows in turbomachinery. The code has been engineered with a high degree of scalability, enabling it to effectively leverage the many-core architecture of the new Sunway system. A consistent performance of 115.8 DP-PFLOPs has been achieved on a high-pressure turbine cascade consisting of over 1.69 billion mesh e… ▽ More A state-of-the-art large eddy simulation code has been developed to solve compressible flows in turbomachinery. The code has been engineered with a high degree of scalability, enabling it to effectively leverage the many-core architecture of the new Sunway system. A consistent performance of 115.8 DP-PFLOPs has been achieved on a high-pressure turbine cascade consisting of over 1.69 billion mesh elements and 865 billion Degree of Freedoms (DOFs). By leveraging a high-order unstructured solver and its portability to large heterogeneous parallel systems, we have progressed towards solving the grand challenge problem outlined by NASA, which involves a time-dependent simulation of a complete engine, incorporating all the aerodynamic and heat transfer components. △ Less

Submitted 29 December, 2023; v1 submitted 12 August, 2023; originally announced August 2023.

Comments: SC23, November, 2023, Denver, CO., USA

Agile Development of Linux Schedulers with Ekiben

Authors: Samantha Miller, Anirudh Kumar, Tanay Vakharia, Tom Anderson, Ang Chen, Danyang Zhuo

Abstract: Kernel task scheduling is important for application performance, adaptability to new hardware, and complex user requirements. However, developing, testing, and debugging new scheduling algorithms in Linux, the most widely used cloud operating system, is slow and difficult. We developed Ekiben, a framework for high velocity development of Linux kernel schedulers. Ekiben schedulers are written in sa… ▽ More Kernel task scheduling is important for application performance, adaptability to new hardware, and complex user requirements. However, developing, testing, and debugging new scheduling algorithms in Linux, the most widely used cloud operating system, is slow and difficult. We developed Ekiben, a framework for high velocity development of Linux kernel schedulers. Ekiben schedulers are written in safe Rust, and the system supports live upgrade of new scheduling policies into the kernel, userspace debugging, and bidirectional communication with applications. A scheduler implemented with Ekiben achieved near identical performance (within 1% on average) to the default Linux scheduler CFS on a wide range of benchmarks. Ekiben is also able to support a range of research schedulers, specifically the Shinjuku scheduler, a locality aware scheduler, and the Arachne core arbiter, with good performance. △ Less

Submitted 26 June, 2023; originally announced June 2023.

Comments: 13 pages, 5 figures, submitted to Eurosys 2024

Synthetic Cross-language Information Retrieval Training Data

Authors: James Mayfield, Eugene Yang, Dawn Lawrie, Samuel Barham, Orion Weller, Marc Mason, Suraj Nair, Scott Miller

Abstract: A key stumbling block for neural cross-language information retrieval (CLIR) systems has been the paucity of training data. The appearance of the MS MARCO monolingual training set led to significant advances in the state of the art in neural monolingual retrieval. By translating the MS MARCO documents into other languages using machine translation, this resource has been made useful to the CLIR co… ▽ More A key stumbling block for neural cross-language information retrieval (CLIR) systems has been the paucity of training data. The appearance of the MS MARCO monolingual training set led to significant advances in the state of the art in neural monolingual retrieval. By translating the MS MARCO documents into other languages using machine translation, this resource has been made useful to the CLIR community. Yet such translation suffers from a number of problems. While MS MARCO is a large resource, it is of fixed size; its genre and domain of discourse are fixed; and the translated documents are not written in the language of a native speaker of the language, but rather in translationese. To address these problems, we introduce the JH-POLO CLIR training set creation methodology. The approach begins by selecting a pair of non-English passages. A generative large language model is then used to produce an English query for which the first passage is relevant and the second passage is not relevant. By repeating this process, collections of arbitrary size can be created in the style of MS MARCO but using naturally-occurring documents in any desired genre and domain of discourse. This paper describes the methodology in detail, shows its use in creating new CLIR training sets, and describes experiments using the newly created training data. △ Less

Submitted 29 April, 2023; originally announced May 2023.

Comments: 11 pages, 4 figures

Impact of Subword Pooling Strategy on Cross-lingual Event Detection

Authors: Shantanu Agarwal, Steven Fincke, Chris Jenkins, Scott Miller, Elizabeth Boschee

Abstract: Pre-trained multilingual language models (e.g., mBERT, XLM-RoBERTa) have significantly advanced the state-of-the-art for zero-shot cross-lingual information extraction. These language models ubiquitously rely on word segmentation techniques that break a word into smaller constituent subwords. Therefore, all word labeling tasks (e.g. named entity recognition, event detection, etc.), necessitate a p… ▽ More Pre-trained multilingual language models (e.g., mBERT, XLM-RoBERTa) have significantly advanced the state-of-the-art for zero-shot cross-lingual information extraction. These language models ubiquitously rely on word segmentation techniques that break a word into smaller constituent subwords. Therefore, all word labeling tasks (e.g. named entity recognition, event detection, etc.), necessitate a pooling strategy that takes the subword representations as input and outputs a representation for the entire word. Taking the task of cross-lingual event detection as a motivating example, we show that the choice of pooling strategy can have a significant impact on the target language performance. For example, the performance varies by up to 16 absolute $f_{1}$ points depending on the pooling strategy when training in English and testing in Arabic on the ACE task. We carry out our analysis with five different pooling strategies across nine languages in diverse multi-lingual datasets. Across configurations, we find that the canonical strategy of taking just the first subword to represent the entire word is usually sub-optimal. On the other hand, we show that attention pooling is robust to language and dataset variations by being either the best or close to the optimal strategy. For reproducibility, we make our code available at https://github.com/isi-boston/ed-pooling. △ Less

Submitted 22 February, 2023; v1 submitted 22 February, 2023; originally announced February 2023.

Partial annotations for the segmentation of large structures with low annotation cost

Authors: Bella Specktor Fadida, Daphna Link Sourani, Liat Ben Sira Elka Miller, Dafna Ben Bashat, Leo Joskowicz

Abstract: Deep learning methods have been shown to be effective for the automatic segmentation of structures and pathologies in medical imaging. However, they require large annotated datasets, whose manual segmentation is a tedious and time-consuming task, especially for large structures. We present a new method of partial annotations that uses a small set of consecutive annotated slices from each scan with… ▽ More Deep learning methods have been shown to be effective for the automatic segmentation of structures and pathologies in medical imaging. However, they require large annotated datasets, whose manual segmentation is a tedious and time-consuming task, especially for large structures. We present a new method of partial annotations that uses a small set of consecutive annotated slices from each scan with an annotation effort that is equal to that of only few annotated cases. The training with partial annotations is performed by using only annotated blocks, incorporating information about slices outside the structure of interest and modifying a batch loss function to consider only the annotated slices. To facilitate training in a low data regime, we use a two-step optimization process. We tested the method with the popular soft Dice loss for the fetal body segmentation task in two MRI sequences, TRUFI and FIESTA, and compared full annotation regime to partial annotations with a similar annotation effort. For TRUFI data, the use of partial annotations yielded slightly better performance on average compared to full annotations with an increase in Dice score from 0.936 to 0.942, and a substantial decrease in Standard Deviations (STD) of Dice score by 22% and Average Symmetric Surface Distance (ASSD) by 15%. For the FIESTA sequence, partial annotations also yielded a decrease in STD of the Dice score and ASSD metrics by 27.5% and 33% respectively for in-distribution data, and a substantial improvement also in average performance on out-of-distribution data, increasing Dice score from 0.84 to 0.9 and decreasing ASSD from 7.46 to 4.01 mm. The two-step optimization process was helpful for partial annotations for both in-distribution and out-of-distribution data. The partial annotations method with the two-step optimizer is therefore recommended to improve segmentation performance under low data regime. △ Less

Submitted 25 September, 2022; originally announced September 2022.

Comments: 10 pages, 4 figures

Journal ref: Medical Image Learning with Limited and Noisy Data. MILLanD 2022. Lecture Notes in Computer Science, vol 13559. Springer, Cham

Distinct Angles and Angle Chains in Three Dimensions

Authors: Ruben Ascoli, Livia Betti, Jacob Lehmann Duke, Xuyan Liu, Wyatt Milgrim, Steven J. Miller, Eyvindur A. Palsson, Francisco Romero Acosta, Santiago Velazquez Iannuzzelli

Abstract: In 1946, Erdős posed the distinct distance problem, which seeks to find the minimum number of distinct distances between pairs of points selected from any configuration of $n$ points in the plane. The problem has since been explored along with many variants, including ones that extend it into higher dimensions. Less studied but no less intriguing is Erdős' distinct angle problem, which seeks to fi… ▽ More In 1946, Erdős posed the distinct distance problem, which seeks to find the minimum number of distinct distances between pairs of points selected from any configuration of $n$ points in the plane. The problem has since been explored along with many variants, including ones that extend it into higher dimensions. Less studied but no less intriguing is Erdős' distinct angle problem, which seeks to find point configurations in the plane that minimize the number of distinct angles. In their recent paper "Distinct Angles in General Position," Fleischmann, Konyagin, Miller, Palsson, Pesikoff, and Wolf use a logarithmic spiral to establish an upper bound of $O(n^2)$ on the minimum number of distinct angles in the plane in general position, which prohibits three points on any line or four on any circle. We consider the question of distinct angles in three dimensions and provide bounds on the minimum number of distinct angles in general position in this setting. We focus on pinned variants of the question, and we examine explicit constructions of point configurations in $\mathbb{R}^3$ which use self-similarity to minimize the number of distinct angles. Furthermore, we study a variant of the distinct angles question regarding distinct angle chains and provide bounds on the minimum number of distinct chains in $\mathbb{R}^2$ and $\mathbb{R}^3$. △ Less

Submitted 19 February, 2023; v1 submitted 28 August, 2022; originally announced August 2022.

Comments: 16 pages, 7 figures

Journal ref: Discrete Mathematics & Theoretical Computer Science, vol. 25:1, Combinatorics (February 27, 2023) dmtcs:10037

Deep Learning Reveals Patterns of Diverse and Changing Sentiments Towards COVID-19 Vaccines Based on 11 Million Tweets

Authors: Hanyin Wang, Meghan R. Hutch, Yikuan Li, Adrienne S. Kline, Sebastian Otero, Leena B. Mithal, Emily S. Miller, Andrew Naidech, Yuan Luo

Abstract: Over 12 billion doses of COVID-19 vaccines have been administered at the time of writing. However, public perceptions of vaccines have been complex. We analyzed COVID-19 vaccine-related tweets to understand the evolving perceptions of COVID-19 vaccines. We finetuned a deep learning classifier using a state-of-the-art model, XLNet, to detect each tweet's sentiment automatically. We employed validat… ▽ More Over 12 billion doses of COVID-19 vaccines have been administered at the time of writing. However, public perceptions of vaccines have been complex. We analyzed COVID-19 vaccine-related tweets to understand the evolving perceptions of COVID-19 vaccines. We finetuned a deep learning classifier using a state-of-the-art model, XLNet, to detect each tweet's sentiment automatically. We employed validated methods to extract the users' race or ethnicity, gender, age, and geographical locations from user profiles. Incorporating multiple data sources, we assessed the sentiment patterns among subpopulations and juxtaposed them against vaccine uptake data to unravel their interactive patterns. 11,211,672 COVID-19 vaccine-related tweets corresponding to 2,203,681 users over two years were analyzed. The finetuned model for sentiment classification yielded an accuracy of 0.92 on testing set. Users from various demographic groups demonstrated distinct patterns in sentiments towards COVID-19 vaccines. User sentiments became more positive over time, upon which we observed subsequent upswing in the population-level vaccine uptake. Surrounding dates where positive sentiments crest, we detected encouraging news or events regarding vaccine development and distribution. Positive sentiments in pregnancy-related tweets demonstrated a delayed pattern compared with trends in general population, with postponed vaccine uptake trends. Distinctive patterns across subpopulations suggest the need of tailored strategies. Global news and events profoundly involved in shaping users' thoughts on social media. Populations with additional concerns, such as pregnancy, demonstrated more substantial hesitancy since lack of timely recommendations. Feature analysis revealed hesitancies of various subpopulations stemmed from clinical trial logics, risks and complications, and urgency of scientific evidence. △ Less

Submitted 5 July, 2022; originally announced July 2022.

Distinct Angles in General Position

Authors: Henry L. Fleischmann, Sergei V. Konyagin, Steven J. Miller, Eyvindur A. Palsson, Ethan Pesikoff, Charles Wolf

Abstract: The Erdős distinct distance problem is a ubiquitous problem in discrete geometry. Somewhat less well known is Erdős' distinct angle problem, the problem of finding the minimum number of distinct angles between $n$ non-collinear points in the plane. Recent work has introduced bounds on a wide array of variants of this problem, inspired by similar variants in the distance setting. In this short no… ▽ More The Erdős distinct distance problem is a ubiquitous problem in discrete geometry. Somewhat less well known is Erdős' distinct angle problem, the problem of finding the minimum number of distinct angles between $n$ non-collinear points in the plane. Recent work has introduced bounds on a wide array of variants of this problem, inspired by similar variants in the distance setting. In this short note, we improve the best known upper bound for the minimum number of distinct angles formed by $n$ points in general position from $O(n^{\log_2(7)})$ to $O(n^2)$. Before this work, similar bounds relied on projections onto a generic plane from higher dimensional space. In this paper, we employ the geometric properties of a logarithmic spiral, sidestepping the need for a projection. We also apply this configuration to reduce the upper bound on the largest integer such that any set of $n$ points in general position has a subset of that size with all distinct angles. This bound is decreased from $O(n^{\log_2(7)/3})$ to $O(n^{1/2})$. △ Less

Submitted 13 June, 2022; v1 submitted 9 June, 2022; originally announced June 2022.

Comments: Former Corollary 4.1 upgraded to Theorem 1.2 with improved bounds

MSC Class: 52C10

Language Model Priming for Cross-Lingual Event Extraction

Authors: Steven Fincke, Shantanu Agarwal, Scott Miller, Elizabeth Boschee

Abstract: We present a novel, language-agnostic approach to "priming" language models for the task of event extraction, providing particularly effective performance in low-resource and zero-shot cross-lingual settings. With priming, we augment the input to the transformer stack's language model differently depending on the question(s) being asked of the model at runtime. For instance, if the model is being… ▽ More We present a novel, language-agnostic approach to "priming" language models for the task of event extraction, providing particularly effective performance in low-resource and zero-shot cross-lingual settings. With priming, we augment the input to the transformer stack's language model differently depending on the question(s) being asked of the model at runtime. For instance, if the model is being asked to identify arguments for the trigger "protested", we will provide that trigger as part of the input to the language model, allowing it to produce different representations for candidate arguments than when it is asked about arguments for the trigger "arrest" elsewhere in the same sentence. We show that by enabling the language model to better compensate for the deficits of sparse and noisy training data, our approach improves both trigger and argument detection and classification significantly over the state of the art in a zero-shot cross-lingual setting. △ Less

Submitted 25 September, 2021; originally announced September 2021.

Source-sink cooperation dynamics constrain institutional evolution in a group-structured society

Authors: Laurent Hébert-Dufresne, Timothy M. Waring, Guillaume St-Onge, Meredith T. Niles, Laura Kati Corlew, Matthew P. Dube, Stephanie J. Miller, Nicholas Gotelli, Brian J. McGill

Abstract: Societies change through time, entailing changes in behaviors and institutions. We ask how social change occurs when behaviors and institutions are interdependent. We model a group-structured society in which the transmission of individual behavior occurs in parallel with the selection of group-level institutions. We consider a cooperative behavior that generates collective benefits for groups but… ▽ More Societies change through time, entailing changes in behaviors and institutions. We ask how social change occurs when behaviors and institutions are interdependent. We model a group-structured society in which the transmission of individual behavior occurs in parallel with the selection of group-level institutions. We consider a cooperative behavior that generates collective benefits for groups but does not spread between individuals on its own. Groups exhibit institutions that increase the diffusion of the behavior within the group, but also incur a group cost. Groups adopt institutions in proportion to their fitness. Finally, cooperative behavior may also spread globally. As expected, we find that cooperation and institutions are mutually reinforcing. But the model also generates behavioral source-sink dynamics when cooperation generated in institutional groups spreads to non-institutional groups, boosting their fitness. Consequently, the global diffusion of cooperation creates a pattern of institutional free-riding that limits the evolution of group-beneficial institutions. Our model suggests that, in a group-structured society, large-scale change in behavior and institutions (i.e. social change) can be best achieved when the two remain correlated, such as through the spread successful pilot programs. △ Less

Submitted 16 September, 2021; originally announced September 2021.

Journal ref: R. Soc. Open Sci. 9: 211743 (2022)

DEGREE: A Data-Efficient Generation-Based Event Extraction Model

Authors: I-Hung Hsu, Kuan-Hao Huang, Elizabeth Boschee, Scott Miller, Prem Natarajan, Kai-Wei Chang, Nanyun Peng

Abstract: Event extraction requires high-quality expert human annotations, which are usually expensive. Therefore, learning a data-efficient event extraction model that can be trained with only a few labeled examples has become a crucial challenge. In this paper, we focus on low-resource end-to-end event extraction and propose DEGREE, a data-efficient model that formulates event extraction as a conditional… ▽ More Event extraction requires high-quality expert human annotations, which are usually expensive. Therefore, learning a data-efficient event extraction model that can be trained with only a few labeled examples has become a crucial challenge. In this paper, we focus on low-resource end-to-end event extraction and propose DEGREE, a data-efficient model that formulates event extraction as a conditional generation problem. Given a passage and a manually designed prompt, DEGREE learns to summarize the events mentioned in the passage into a natural sentence that follows a predefined pattern. The final event predictions are then extracted from the generated sentence with a deterministic algorithm. DEGREE has three advantages to learn well with less training data. First, our designed prompts provide semantic guidance for DEGREE to leverage DEGREE and thus better capture the event arguments. Moreover, DEGREE is capable of using additional weakly-supervised information, such as the description of events encoded in the prompts. Finally, DEGREE learns triggers and arguments jointly in an end-to-end manner, which encourages the model to better utilize the shared knowledge and dependencies among them. Our experimental results demonstrate the strong performance of DEGREE for low-resource event extraction. △ Less

Submitted 3 May, 2022; v1 submitted 28 August, 2021; originally announced August 2021.

Comments: Paper accepted by NAACL 2022. The first two authors contribute equally. Our code and models can be found at https://github.com/PlusLabNLP/DEGREE

Distinct Angle Problems and Variants

Authors: Henry L. Fleischmann, Hongyi B. Hu, Faye Jackson, Steven J. Miller, Eyvindur A. Palsson, Ethan Pesikoff, Charles Wolf

Abstract: The Erdős distinct distance problem is a ubiquitous problem in discrete geometry. Less well known is Erdős' distinct angle problem, the problem of finding the minimum number of distinct angles between $n$ non-collinear points in the plane. The standard problem is already well understood. However, it admits many of the same variants as the distinct distance problem, many of which are unstudied. W… ▽ More The Erdős distinct distance problem is a ubiquitous problem in discrete geometry. Less well known is Erdős' distinct angle problem, the problem of finding the minimum number of distinct angles between $n$ non-collinear points in the plane. The standard problem is already well understood. However, it admits many of the same variants as the distinct distance problem, many of which are unstudied. We provide upper and lower bounds on a broad class of distinct angle problems. We show that the number of distinct angles formed by $n$ points in general position is $O(n^{\log_2(7)})$, providing the first non-trivial bound for this quantity. We introduce a new class of asymptotically optimal point configurations with no four cocircular points. Then, we analyze the sensitivity of asymptotically optimal point sets to perturbation, yielding a much broader class of asymptotically optimal configurations. In higher dimensions we show that a variant of Lenz's construction admits fewer distinct angles than the optimal configurations in two dimensions. We also show that the minimum size of a maximal subset of $n$ points in general position admitting only unique angles is $Ω(n^{1/5})$ and $O(n^{\log_2(7)/3})$. We also provide bounds on the partite variants of the standard distinct angle problem. △ Less

Submitted 26 August, 2021; originally announced August 2021.

MSC Class: 05

Blending Knowledge in Deep Recurrent Networks for Adverse Event Prediction at Hospital Discharge

Authors: Prithwish Chakraborty, James Codella, Piyush Madan, Ying Li, Hu Huang, Yoonyoung Park, Chao Yan, Ziqi Zhang, Cheng Gao, Steve Nyemba, Xu Min, Sanjib Basak, Mohamed Ghalwash, Zach Shahn, Parthasararathy Suryanarayanan, Italo Buleje, Shannon Harrer, Sarah Miller, Amol Rajmane, Colin Walsh, Jonathan Wanderer, Gigi Yuen Reed, Kenney Ng, Daby Sow, Bradley A. Malin

Abstract: Deep learning architectures have an extremely high-capacity for modeling complex data in a wide variety of domains. However, these architectures have been limited in their ability to support complex prediction problems using insurance claims data, such as readmission at 30 days, mainly due to data sparsity issue. Consequently, classical machine learning methods, especially those that embed domain… ▽ More Deep learning architectures have an extremely high-capacity for modeling complex data in a wide variety of domains. However, these architectures have been limited in their ability to support complex prediction problems using insurance claims data, such as readmission at 30 days, mainly due to data sparsity issue. Consequently, classical machine learning methods, especially those that embed domain knowledge in handcrafted features, are often on par with, and sometimes outperform, deep learning approaches. In this paper, we illustrate how the potential of deep learning can be achieved by blending domain knowledge within deep learning architectures to predict adverse events at hospital discharge, including readmissions. More specifically, we introduce a learning architecture that fuses a representation of patient data computed by a self-attention based recurrent neural network, with clinically relevant features. We conduct extensive experiments on a large claims dataset and show that the blended method outperforms the standard machine learning approaches. △ Less

Submitted 9 April, 2021; originally announced April 2021.

Comments: Presented at the AMIA 2021 Virtual Informatics Summit

Question-Driven Design Process for Explainable AI User Experiences

Authors: Q. Vera Liao, Milena Pribić, Jaesik Han, Sarah Miller, Daby Sow

Abstract: A pervasive design issue of AI systems is their explainability--how to provide appropriate information to help users understand the AI. The technical field of explainable AI (XAI) has produced a rich toolbox of techniques. Designers are now tasked with the challenges of how to select the most suitable XAI techniques and translate them into UX solutions. Informed by our previous work studying desig… ▽ More A pervasive design issue of AI systems is their explainability--how to provide appropriate information to help users understand the AI. The technical field of explainable AI (XAI) has produced a rich toolbox of techniques. Designers are now tasked with the challenges of how to select the most suitable XAI techniques and translate them into UX solutions. Informed by our previous work studying design challenges around XAI UX, this work proposes a design process to tackle these challenges. We review our and related prior work to identify requirements that the process should fulfill, and accordingly, propose a Question-Driven Design Process that grounds the user needs, choices of XAI techniques, design, and evaluation of XAI UX all in the user questions. We provide a mapping guide between prototypical user questions and exemplars of XAI techniques to reframe the technical space of XAI, also serving as boundary objects to support collaboration between designers and AI engineers. We demonstrate it with a use case of designing XAI for healthcare adverse events prediction, and discuss lessons learned for tackling design challenges of AI systems. △ Less

Submitted 3 September, 2021; v1 submitted 7 April, 2021; originally announced April 2021.

Comments: working paper

Generating cryptographically-strong random lattice bases and recognizing rotations of $\mathbb{Z}^n$

Authors: Tamar Lichter Blanks, Stephen D. Miller

Abstract: Lattice-based cryptography relies on generating random bases which are difficult to fully reduce. Given a lattice basis (such as the private basis for a cryptosystem), all other bases are related by multiplication by matrices in $GL(n,\mathbb{Z})$. We compare the strengths of various methods to sample random elements of $GL(n,\mathbb{Z})$, finding some are stronger than others with respect to the… ▽ More Lattice-based cryptography relies on generating random bases which are difficult to fully reduce. Given a lattice basis (such as the private basis for a cryptosystem), all other bases are related by multiplication by matrices in $GL(n,\mathbb{Z})$. We compare the strengths of various methods to sample random elements of $GL(n,\mathbb{Z})$, finding some are stronger than others with respect to the problem of recognizing rotations of the $\mathbb{Z}^n$ lattice. In particular, the standard algorithm of multiplying unipotent generators together (as implemented in Magma's RandomSLnZ command) generates instances of this last problem which can be efficiently broken, even in dimensions nearing 1,500. Likewise, we find that the random basis generation method in one of the NIST Post-Quantum Cryptography competition submissions (DRS) generates instances which can be efficiently broken, even at its 256-bit security settings. Other random basis generation algorithms (some older, some newer) are described which appear to be much stronger. △ Less

Submitted 19 May, 2021; v1 submitted 11 February, 2021; originally announced February 2021.

Comments: 20 pages, 2 figures, to appear in PQCrypto 2021

Forecasting Hamiltonian dynamics without canonical coordinates

Authors: Anshul Choudhary, John F. Lindner, Elliott G. Holliday, Scott T. Miller, Sudeshna Sinha, William L. Ditto

Abstract: Conventional neural networks are universal function approximators, but because they are unaware of underlying symmetries or physical laws, they may need impractically many training data to approximate nonlinear dynamics. Recently introduced Hamiltonian neural networks can efficiently learn and forecast dynamical systems that conserve energy, but they require special inputs called canonical coordin… ▽ More Conventional neural networks are universal function approximators, but because they are unaware of underlying symmetries or physical laws, they may need impractically many training data to approximate nonlinear dynamics. Recently introduced Hamiltonian neural networks can efficiently learn and forecast dynamical systems that conserve energy, but they require special inputs called canonical coordinates, which may be hard to infer from data. Here we significantly expand the scope of such networks by demonstrating a simple way to train them with any set of generalised coordinates, including easily observable ones. △ Less

Submitted 28 October, 2020; originally announced October 2020.

Comments: 7 pages, 4 figures

Mastering high-dimensional dynamics with Hamiltonian neural networks

Authors: Scott T. Miller, John F. Lindner, Anshul Choudhary, Sudeshna Sinha, William L. Ditto

Abstract: We detail how incorporating physics into neural network design can significantly improve the learning and forecasting of dynamical systems, even nonlinear systems of many dimensions. A map building perspective elucidates the superiority of Hamiltonian neural networks over conventional neural networks. The results clarify the critical relation between data, dimension, and neural network learning pe… ▽ More We detail how incorporating physics into neural network design can significantly improve the learning and forecasting of dynamical systems, even nonlinear systems of many dimensions. A map building perspective elucidates the superiority of Hamiltonian neural networks over conventional neural networks. The results clarify the critical relation between data, dimension, and neural network learning performance. △ Less

Submitted 28 July, 2020; originally announced August 2020.

Comments: 7 pages, 9 figures