20 citations · 30 across the 12 of their papers we have counts for
12 papers
Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss
Thomas T. Zhang, Alok Shah, Yifei Zhang +3
Many modern applications of deep learning involve training a neural network via a one-step prediction loss (e.g., regression, cross-entropy), but deploy the network by rollin…
Regret Analysis of Multi-task Representation Learning for Linear-Quadratic Adaptive Control
Bruce D. Lee, Leonardo F. Toso, Thomas T. Zhang +2
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…
Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic Data
Thomas T. C. K. Zhang, Leonardo F. Toso, James Anderson +1
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 a…
Performance-Robustness Tradeoffs in Adversarially Robust Control and Estimation
Bruce D. Lee, Thomas T. C. K. Zhang, Hamed Hassani +1
While methods can introduce robustness against worst-case perturbations, their nominal performance under conventional stochastic disturbances is often drastica…
Multi-Task Imitation Learning for Linear Dynamical Systems
Thomas T. Zhang, Katie Kang, Bruce D. Lee +4
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-train…
TaSIL: Taylor Series Imitation Learning
Daniel Pfrommer, Thomas T. C. K. Zhang, Stephen Tu +1
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 t…
Performance-Robustness Tradeoffs in Adversarially Robust Linear-Quadratic Control
Bruce D. Lee, Thomas T. C. K. Zhang, Hamed Hassani +1
While methods can introduce robustness against worst-case perturbations, their nominal performance under conventional stochastic disturbances is often drastica…
Adversarially Robust Stability Certificates can be Sample-Efficient
Thomas T. C. K. Zhang, Stephen Tu, Nicholas M. Boffi +2
Motivated by bridging the simulation to reality gap in the context of safety-critical systems, we consider learning adversarially robust stability certificates for unknown nonlinea…
Adversarial Tradeoffs in Robust State Estimation
Thomas T. C. K. Zhang, Bruce D. Lee, Hamed Hassani +1
Adversarially robust training has been shown to reduce the susceptibility of learned models to targeted input data perturbations. However, it has also been observed that such adver…
Biwhitening Reveals the Rank of a Count Matrix
Boris Landa, Thomas T. C. K. Zhang, Yuval Kluger
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 w…
Sparse Optimization on General Atomic Sets: Greedy and Forward-Backward Algorithms
Thomas Zhang
We consider the problem of sparse atomic optimization, where the notion of "sparsity" is generalized to meaning some linear combination of few atoms. The definition of atomic set i…
On the continuous Fermat-Weber problem for a convex polygon using Euclidean distance
Thomas T. C. K. Zhang, John Gunnar Carlsson
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 expr…