Scholar
Kaixuan Ji
Google Scholar ID: FOoKDukAAAAJ
University of California, Los Angeles
machine learning
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
2,659
H-index
7
i10-index
7
Publications
12
Co-authors
9
list available
Publications
9 items
Bandits with Multiple Optimal Arms: Minimax Regret and Non-Adaptivit
2026
Cited
0
Understanding Off- vs On-Policy Distillation: A Tale of Distinct Training Objectives
2026
Cited
0
Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability
2026
Cited
0
On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization
2026
Cited
0
Near-Optimal Regret for KL-Regularized Multi-Armed Bandits
2026
Cited
0
Best-of-Majority: Minimax-Optimal Strategy for Pass@$k$ Inference Scaling
2025
Cited
0
Nearly Optimal Sample Complexity of Offline KL-Regularized Contextual Bandits under Single-Policy Concentrability
2025
Cited
0
Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization
arXiv.org · 2024
Cited
3
Load more
Co-authors
9 total
Quanquan Gu
Associate Professor of Computer Science, UCLA
Xiao Liu
Tsinghua University
Yicheng Fu
Stanford University
Tang Jie
WeBank Chair Professor, Tsinghua University
Zhengxiao Du
清华大学
Jiafan He
PhD student, Department of Computer Science, UCLA
Ji Qi
Tsinghua University
Qingyue Zhao
University of California, Los Angeles
