Preprints and Publications

Preprints

• Heavy-Tailed Linear Bandits: Adversarial Robustness, Best-of-Both-Worlds, and Beyond. [arXiv]
  Canzhe Zhao*, Shinji Ito*, Shuai Li.
  Under review, 2025.

Publications

2025

• Learning Imperfect Information Extensive-form Games with Last-iterate Convergence under Bandit Feedback.
  Canzhe Zhao, Yutian Cheng, Jing Dong, Baoxiang Wang, Shuai Li.
  ICML, 2025.

• Towards Provably Efficient Learning of Imperfect Information Extensive-Form Games with Linear Function Approximation.
  Canzhe Zhao, Shuze Chen, Weiming Liu, Haobo Fu, Qiang Fu, Shuai Li.
  UAI, 2025.

• Logarithmic Regret for Linear Markov Decision Processes with Adversarial Corruptions.
  Canzhe Zhao, Xiangcheng Zhang, Baoxiang Wang, Shuai Li.
  AAAI, 2025.

2023

• Learning Adversarial Low-rank Markov Decision Processes with Unknown Transition and Full-information Feedback. [arXiv][poster]
  Canzhe Zhao, Ruofeng Yang, Baoxiang Wang, Xuezhou Zhang, Shuai Li.
  NeurIPS, 2023.

• Best-of-Three-Worlds Analysis for Linear Bandits with Follow-the-Regularized-Leader algorithm. [arXiv]
  Fang Kong, Canzhe Zhao, Shuai Li.
  COLT, 2023.

• DPMAC: Differentially Private Communication for Cooperative Multi-Agent Reinforcement Learning.
  Canzhe Zhao*, Yanjie Ze*, Jing Dong, Baoxiang Wang, Shuai Li.
  IJCAI, 2023.

• Learning Adversarial Linear Mixture Markov Decision Processes with Bandit Feedback and Unknown Transition. [link][slides]
  Canzhe Zhao, Ruofeng Yang, Baoxiang Wang, Shuai Li.
  ICLR, 2023

• Clustering of Conversational Bandits with Posterior Sampling for User Preference Learning and Elicitation. [link]
  Qizhi Li*, Canzhe Zhao*, Tong Yu, Junda Wu, Shuai Li.
  UMUAI, 2023

• Differentially Private Temporal Difference Learning with Stochastic Nonconvex-Strongly-Concave Optimization. [link]
  Canzhe Zhao, Yanjie Ze, Jing Dong, Baoxiang Wang, Shuai Li.
  WSDM, 2023.

2022

• Knowledge-aware Conversational Preference Elicitation with Bandit Feedback. [link] [slides]
  Canzhe Zhao, Tong Yu, Zhihui Xie, Shuai Li.
  WWW, 2022.

• Simultaneously Learning Stochastic and Adversarial Bandits under the Position-based Model. [arXiv]
  Cheng Chen, Canzhe Zhao, Shuai Li.
  AAAI, 2022.

2021

• Clustering of Conversational Bandits for User Preference Learning and Elicitation. [link][slides]
  Junda Wu*, Canzhe Zhao*, Tong Yu, Jingyang Li, Shuai Li.
  CIKM, 2021.

• Comparison-based Conversational Recommender System with Relative Bandit Feedback. [link]
  Zhihui Xie, Tong Yu, Canzhe Zhao, Shuai Li.
  SIGIR, 2021.