Skip to main content

Showing 1–11 of 11 results for author: Zhang, T T

Searching in archive cs. Search in all archives.
.
  1. arXiv:2507.09061  [pdf, ps, other

    cs.LG eess.SY stat.ML

    Action Chunking and Exploratory Data Collection Yield Exponential Improvements in Behavior Cloning for Continuous Control

    Authors: Thomas T. Zhang, Daniel Pfrommer, Chaoyi Pan, Nikolai Matni, Max Simchowitz

    Abstract: This paper presents a theoretical analysis of two of the most impactful interventions in modern learning from demonstration in robotics and continuous control: the practice of action-chunking (predicting sequences of actions in open-loop) and exploratory augmentation of expert demonstrations. Though recent results show that learning from demonstration, also known as imitation learning (IL), can su… ▽ More

    Submitted 26 November, 2025; v1 submitted 11 July, 2025; originally announced July 2025.

    Comments: Updated manuscript. New visualization figures and control-theory primer

  2. arXiv:2502.01763  [pdf, other

    cs.LG math.OC stat.ML

    On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning

    Authors: Thomas T. Zhang, Behrad Moniri, Ansh Nagwekar, Faraz Rahman, Anton Xue, Hamed Hassani, Nikolai Matni

    Abstract: Layer-wise preconditioning methods are a family of memory-efficient optimization algorithms that introduce preconditioners per axis of each layer's weight tensors. These methods have seen a recent resurgence, demonstrating impressive performance relative to entry-wise ("diagonal") preconditioning methods such as Adam(W) on a wide range of neural network optimization tasks. Complementary to their p… ▽ More

    Submitted 3 February, 2025; originally announced February 2025.

  3. arXiv:2410.11227  [pdf, other

    stat.ML cs.LG eess.SY

    Guarantees for Nonlinear Representation Learning: Non-identical Covariates, Dependent Data, Fewer Samples

    Authors: Thomas T. Zhang, Bruce D. Lee, Ingvar Ziemann, George J. Pappas, Nikolai Matni

    Abstract: A driving force behind the diverse applicability of modern machine learning is the ability to extract meaningful features across many sources. However, many practical domains involve data that are non-identically distributed across sources, and statistically dependent within its source, violating vital assumptions in existing theoretical studies. Toward addressing these issues, we establish statis… ▽ More

    Submitted 14 October, 2024; originally announced October 2024.

    Comments: Appeared at ICML 2024

  4. arXiv:2407.05781  [pdf, other

    cs.LG eess.SY

    Regret Analysis of Multi-task Representation Learning for Linear-Quadratic Adaptive Control

    Authors: Bruce D. Lee, Leonardo F. Toso, Thomas T. Zhang, James Anderson, Nikolai Matni

    Abstract: Representation learning is a powerful tool that enables learning over large multitudes of agents or domains by enforcing that all agents operate on a shared set of learned features. However, many robotics or controls applications that would benefit from collaboration operate in settings with changing environments and goals, whereas most guarantees for representation learning are stated for static… ▽ More

    Submitted 27 July, 2024; v1 submitted 8 July, 2024; originally announced July 2024.

  5. arXiv:2308.04428  [pdf, other

    stat.ML cs.LG eess.SY

    Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic Data

    Authors: Thomas T. C. K. Zhang, Leonardo F. Toso, James Anderson, Nikolai Matni

    Abstract: A powerful concept behind much of the recent progress in machine learning is the extraction of common features across data from heterogeneous sources or tasks. Intuitively, using all of one's data to learn a common representation function benefits both computational effort and statistical generalization by leaving a smaller number of parameters to fine-tune on a given task. Toward theoretically gr… ▽ More

    Submitted 12 October, 2024; v1 submitted 8 August, 2023; originally announced August 2023.

    Comments: Appeared at ICLR 2024 (spotlight presentation)

  6. arXiv:2212.00186  [pdf, other

    cs.LG eess.SY

    Multi-Task Imitation Learning for Linear Dynamical Systems

    Authors: Thomas T. Zhang, Katie Kang, Bruce D. Lee, Claire Tomlin, Sergey Levine, Stephen Tu, Nikolai Matni

    Abstract: We study representation learning for efficient imitation learning over linear systems. In particular, we consider a setting where learning is split into two phases: (a) a pre-training step where a shared $k$-dimensional representation is learned from $H$ source policies, and (b) a target policy fine-tuning step where the learned representation is used to parameterize the policy class. We find that… ▽ More

    Submitted 9 November, 2023; v1 submitted 30 November, 2022; originally announced December 2022.

    Comments: Appeared in L4DC 2023. V3: corrected typo in assumptions

  7. arXiv:2205.14812  [pdf, other

    cs.LG

    TaSIL: Taylor Series Imitation Learning

    Authors: Daniel Pfrommer, Thomas T. C. K. Zhang, Stephen Tu, Nikolai Matni

    Abstract: We propose Taylor Series Imitation Learning (TaSIL), a simple augmentation to standard behavior cloning losses in the context of continuous control. TaSIL penalizes deviations in the higher-order Taylor series terms between the learned and expert policies. We show that experts satisfying a notion of $\textit{incremental input-to-state stability}$ are easy to learn, in the sense that a small TaSIL-… ▽ More

    Submitted 16 January, 2023; v1 submitted 29 May, 2022; originally announced May 2022.

    Comments: Appeared at NeurIPS 2022. V2: added to related work, updated notation, fixed small errors in appendix

  8. Spatial-Temporal Map Vehicle Trajectory Detection Using Dynamic Mode Decomposition and Res-UNet+ Neural Networks

    Authors: Tianya T. Zhang, Peter J. Jin

    Abstract: This paper presents a machine-learning-enhanced longitudinal scanline method to extract vehicle trajectories from high-angle traffic cameras. The Dynamic Mode Decomposition (DMD) method is applied to extract vehicle strands by decomposing the Spatial-Temporal Map (STMap) into the sparse foreground and low-rank background. A deep neural network named Res-UNet+ was designed for the semantic segmenta… ▽ More

    Submitted 12 January, 2022; originally announced January 2022.

  9. arXiv:2112.10690  [pdf, other

    cs.LG eess.SY

    Adversarially Robust Stability Certificates can be Sample-Efficient

    Authors: Thomas T. C. K. Zhang, Stephen Tu, Nicholas M. Boffi, Jean-Jacques E. Slotine, Nikolai Matni

    Abstract: Motivated by bridging the simulation to reality gap in the context of safety-critical systems, we consider learning adversarially robust stability certificates for unknown nonlinear dynamical systems. In line with approaches from robust control, we consider additive and Lipschitz bounded adversaries that perturb the system dynamics. We show that under suitable assumptions of incremental stability… ▽ More

    Submitted 20 December, 2021; originally announced December 2021.

    MSC Class: 93D05; 93D09

  10. arXiv:2103.13840  [pdf, other

    math.ST cs.IT

    Biwhitening Reveals the Rank of a Count Matrix

    Authors: Boris Landa, Thomas T. C. K. Zhang, Yuval Kluger

    Abstract: Estimating the rank of a corrupted data matrix is an important task in data analysis, most notably for choosing the number of components in PCA. Significant progress on this task was achieved using random matrix theory by characterizing the spectral properties of large noise matrices. However, utilizing such tools is not straightforward when the data matrix consists of count random variables, e.g.… ▽ More

    Submitted 2 November, 2021; v1 submitted 25 March, 2021; originally announced March 2021.

    MSC Class: 62H12; 62H25

  11. arXiv:1403.3715  [pdf, other

    cs.CG math.OC

    On the continuous Fermat-Weber problem for a convex polygon using Euclidean distance

    Authors: Thomas T. C. K. Zhang, John Gunnar Carlsson

    Abstract: We consider the continuous Fermat-Weber problem, where the customers are continuously (uniformly) distributed along the boundary of a convex polygon. We derive the closed-form expression for finding the average distance from a given point to the continuously distributed customers along the boundary. A Weiszfeld-type procedure is proposed for this model, which is shown to be linearly convergent. We… ▽ More

    Submitted 14 March, 2014; originally announced March 2014.