|
Talks
-
One-Pass Bandit Learning for RLHF and Function Approximation
2025.09.21, 2025 RL China, Beijing.
-
One-Pass Bandit Learning: Nonlinear Reward and Heavy-tailed Noise
2025.07.22, 2025 INFORMS International Meeting, Singapore.
-
Online Ensemble: A Theoretical Framework for Non-stationary Online Learning
2025.05.31, 桂林电子科技大学·计算机与信息安全学院, 广西桂林.
-
Provable Efficiency in Online RL: Function Approximation and RLHF
2025.04.29, NUS ISEM Department Seminar, Singapore.
-
Gradient-Variation Online Learning: Theory and Applications
2024.06.07, LAMDA-RIKENAIP joint workshop on ML, Nanjing.
-
Universal Online Learning with Gradient-Variation Regret
2023.12.18, UC Santa Barbara, US.
-
Online Ensemble: A Theoretical Framework for Non-stationary Online Learning
2023.11.23, HKUST (Guangzhou) AI Seminar, Guangzhou.
-
在线集成：非稳态在线学习的理论框架
2023.11.04, 第二十一届机器学习及其应用研讨会 (MLA 2023), 南京.
-
基于"在线集成"框架的非稳态在线学习.
2023.06.10, 第十二届江苏省计算机大会 (JSCC 2023)·人工智能前沿论坛, 江苏溧阳.
-
Non-stationary Online Learning: An Online Ensemble Framework
2022.11.03, 中国人民大学·高瓴人工智能学院, 北京.
-
Bandit Convex Optimization in Non-stationary Environments
2021.07.10, CSIAM-BDAI 2021·在线学习与优化论坛, 四川成都.
[go back]
|