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.· arXiv.org· 4 citations· ⚡1
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
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.· arXiv.org· 0 citations
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.