collaborators

11 papers

cs.LG2026

Breaking the Total Variance Barrier: Sharp Sample Complexity for Linear Heteroscedastic Bandits with Fixed Action Set

Heyang Zhao, Tianyuan Jin, Weixin Wang +3

Recent years have witnessed increasing interests in tackling heteroscedastic noise in bandits and reinforcement learning. In these works, the cumulative variance of the noise $Λ=…

cs.CL2026

Multi-Mask Diffusion Language Models for Few-Step Generation

Sijin Chen, Yinuo Ren, Heyang Zhao +3

Masked diffusion models (MDMs) are a promising family of language generators, but achieving high-quality few-step generation remains challenging. In MDMs, all forward trajectories…

cs.LG2026

Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability

Qingyue Zhao, Kaixuan Ji, Heyang Zhao +1

\emph{Kullback-Leibler} (KL) regularization is ubiquitous in reinforcement learning algorithms in the form of \emph{reverse} or \emph{forward} KL. Recent studies have demonstrated…

cs.LG2026

On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization

Kaixuan Ji, Qiwei Di, Heyang Zhao +2

Kullback-Leibler (KL) regularization is widely used in offline decision-making and offers several benefits, motivating recent work on the sample complexity of offline learning with…

cs.LG2026

Logarithmic Regret for Online KL-Regularized Reinforcement Learning

Heyang Zhao, Chenlu Ye, Wei Xiong +2

Recent advances in Reinforcement Learning from Human Feedback (RLHF) have shown that KL-regularization plays a pivotal role in improving the efficiency of RL fine-tuning for large…

cs.LG2026

Near-Optimal Regret for KL-Regularized Multi-Armed Bandits

Kaixuan Ji, Qingyue Zhao, Heyang Zhao +2

Recent studies have shown that reinforcement learning with KL-regularized objectives can enjoy faster rates of convergence or logarithmic regret, in contrast to the classical $\sqr…