Authors

Hengyu Fu

Publications 2

Preprint Open access

Principal Component Regression Dominates all Monotone Spectral Filters for Linear Regression

Juno Kim, Hengyu Fu, Peter Bartlett et al. · 2026

We compare the instance-wise, finite-sample risks of monotone spectral filters for linear regression, a broad class of estimators including principal component regression (PCR), gradient descent (GD), and ridge regression. We show that PCR dominates all monotone spectral filters: compared to any such filter, the risk o …

Preprint Open access

Where the Model Changes Its Mind: Hindsight-Divergence Localization for Efficient Reinforcement Learning with Verifiable Rewards

Fanchao Chen, Hengyu Fu, Shivaram Venkataraman et al. · 2026

Group-relative methods for reinforcement learning with verifiable rewards (RLVR) learn from differences in rollout outcomes. Independently sampling complete trajectories is costly and does not explicitly explore the decision space at critical positions. Feedback on a completed trajectory can reveal which earlier choice …

Co-authors

Juno Kim Peter Bartlett Jason D. Lee Jingfeng Wu Fanchao Chen Shivaram Venkataraman Jiantao Jiao