publications

in reverse chronological order.

2026

  1. arXiv
    Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss
    Thomas T. Zhang, Alok Shah, Yifei Zhang, Vincent Zhang, Nikolai Matni, and Max Simchowitz
    Submitted , 2026
  2. ICLR
    Action Chunking and Exploratory Data Collection Yield Exponential Improvements in Behavior Cloning for Continuous Control
    In International Conference on Learning Representations (ICLR), 2026

2025

  1. ICML
    On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning
    Thomas T. Zhang, Behrad Moniri, Ansh Nagwekar, Faraz Rahman, Anton Xue, Hamed Hassani, and Nikolai Matni
    In International Conference on Machine Learning (ICML), 2025

2024

  1. AAAI
    Regret Analysis of Multi-task Representation Learning for Linear-Quadratic Adaptive Control
    In AAAI Conference on Artificial Intelligence, 2024
  2. ICML
    Guarantees for Nonlinear Representation Learning: Non-identical Covariates, Dependent Data, Fewer Samples
    In International Conference on Machine Learning (ICML), 2024
  3. ICLR
    Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic Data
    Thomas T. C. K. Zhang, Leonardo F. Toso, James Anderson, and Nikolai Matni
    In International Conference on Learning Representations (ICLR), 2024

2023

  1. TAC
    Performance-Robustness Tradeoffs in Adversarially Robust Control and Estimation
    Bruce D. Lee, Thomas T. C. K. Zhang, Hamed Hassani, and Nikolai Matni
    IEEE Transactions on Automatic Control, 2023
  2. L4DC
    Multi-Task Imitation Learning for Linear Dynamical Systems
    In Learning for Dynamics and Control Conference (L4DC), 2023
  3. ACC
    Adversarial Tradeoffs in Robust State Estimation
    Thomas T. C. K. Zhang, Bruce D. Lee, Hamed Hassani, and Nikolai Matni
    In American Control Conference (ACC), 2023

2022

  1. NeurIPS
    TaSIL: Taylor Series Imitation Learning
    Daniel Pfrommer, Thomas T. C. K. Zhang, Stephen Tu, and Nikolai Matni
    In Advances in Neural Information Processing Systems (NeurIPS), 2022
  2. CDC
    Performance-Robustness Tradeoffs in Adversarially Robust Linear-Quadratic Control
    Bruce D. Lee, Thomas T. C. K. Zhang, Hamed Hassani, and Nikolai Matni
    In IEEE Conference on Decision and Control (CDC), 2022
  3. L4DC
    Adversarially Robust Stability Certificates can be Sample-Efficient
    In Learning for Dynamics and Control Conference (L4DC), 2022

2021

  1. SIMODS
    Biwhitening Reveals the Rank of a Count Matrix
    Boris Landa, Thomas T. C. K. Zhang, and Yuval Kluger
    SIAM Journal on Mathematics of Data Science, 2021

2019

  1. arXiv
    Sparse Optimization on General Atomic Sets: Greedy and Forward-Backward Algorithms
    Thomas Zhang
    Preprint , 2019

2014

  1. arXiv
    On the continuous Fermat-Weber problem for a convex polygon using Euclidean distance
    Thomas T. C. K. Zhang and John Gunnar Carlsson
    2014