Yuejie Chi

Covariance tracking from sketches of rapid data streams

2015

Estimating and tracking the covariance matrix of high-dimensional data streams with low complexities in acquisition, storage and computation are of great interest in modern data-intensive applications. This paper develops an online covariance estimation and tracking …

Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization

2020 · arXiv (Cornell University)

Natural policy gradient (NPG) methods are among the most widely used policy optimization algorithms in contemporary reinforcement learning. This class of methods is often applied in conjunction with entropy regularization -- an algorithmic scheme that …

Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation

2023 · arXiv (Cornell University)

Robustness has been extensively studied in reinforcement learning (RL) to handle various forms of uncertainty such as random perturbations, rare events, and malicious attacks. In this work, we consider one critical type of robustness against …