4 citations · 9 across the 17 of their papers we have counts for
7 papers · 1 filter
Understanding Off- vs On-Policy Distillation: A Tale of Distinct Training Objectives
Qiwei Di, Xuheng Li, Kaixuan Ji +3
On-policy distillation (OPD) learns from teacher feedback on student-generated responses and has shown promise in reducing forgetting relative to supervised fine-tuning (SFT). Howe…
Bandits with Multiple Optimal Arms: Minimax Regret and Non-Adaptivity
Kaixuan Ji, Qiwei Di, Qingyue Zhao +2
We study multi-armed bandits (MAB) with multiple optimal arms, motivated by the fact that many practical decision making problems admit multiple correct answers. For -armed band…
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= \…
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…
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…
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…
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…