Skip to content

Author

He-Yang Zhao

We have 4 of 25 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

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

A sharp analysis of KL-PCB (Zhao et al., 2026), showing that it achieves a sample complexity of $\tilde{O}(\eta SAC^{\pi^*}/\epsilon)$ under large regularization and a sample complexity of $\tilde{\Omega}(SAC^{\pi^*}/\epsilon^2)$ under small regularization.

Kaixuan Ji, Qi-Wei Di, He-Yang Zhao et al. · 4 citations · ⚡1
#artificial intelligence Preprint Sep 2026

Understanding Off- vs On-Policy Distillation: A Tale of Distinct Training Objectives

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). However, its benefits and fragility remain incompletely understood. We study sequential distillation from multiple teachers, where the student m...

Qi-Wei Di, Xu-Heng Li, Kaixuan Ji et al. · 0 citations

Bandits with Multiple Optimal Arms: Minimax Regret and Non-Adaptivity

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 $K$-armed bandits with $A$ optimal arms, we first provide a sharper analysis of previous sub-sampling algorithms (De Heide et al., 2021; Zhu and Nowak, 20...

Kaixuan Ji, Qi-Wei Di, Qing-Yue Zhao et al. · 0 citations

Multi-Mask Diffusion Language Models for Few-Step Generation

This work proposes a multi-mask diffusion model (MultiMDM) that preserves the masking structure towards few-step generation and derives a closed-form ELBO training objective for MultiMDM that supports continual training from pretrained MDMs.

Sijin Chen, Yinuo Ren, Heyang Zhao et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.