Previous Homepage:

Google Scholar | WikiCFP | t-test |

Peilin Zhao

Principal Researcher
Tencent AI Lab
Shenzhen, China
Email: peilinzhao[AT]

Internship: We are looking for interns, who are interested in Large Language Model, Reinforcement Learning etc.


Peilin Zhao is currently a principal researcher at Tencent AI Lab in China. Previously, he worked at Rutgers University, A*STAR (Agency for Science, Technology and Research), and Ant Group. His research interests include: online learning, recommendation systems, automatic machine learning, deep graph learning, and reinforcement learning, among others. He has been invited to serve as area chair or associate editor at leading international conferences and journals such as ICML, TPAMI, etc. He received a bachelor’s degree in mathematics from Zhejiang University, and a Ph.D. degree in computer science from Nanyang Technological University.

Working Experiences

Education Experiences

Research Interests

Large Language Model, Reinforcement Learning, Deep Graph Learning, Automatic Machine Learning, Recommendation System, and Online Learning.

Selected Publications (Full List)

Meta-learning Hyperparameter Performance Prediction with Neural Processes. ICML 2021
Ying Wei, Peilin Zhao, Junzhou Huang

Adversarial Sparse Transformer for Time Series Forecasting. NeurIPS 2020
Sifan Wu, Xi Xiao, Qianggang Ding, Peilin Zhao, Ying Wei, Junzhou Huang

Hyperparameter Learning via Distributional Transfer. NeurIPS 2019
Ho Chung Leon Law, Peilin Zhao, Leung Sing Chan, Junzhou Huang, Dino Sejdinovic

Towards More Efficient Stochastic Decentralized Learning: Faster Convergence and Sparse Communication. ICML 2018
Zebang Shen, Aryan Mokhtari, Tengfei Zhou, Peilin Zhao, Hui Qian

Projection-free Distributed Online Learning in Networks. ICML 2017
Wenpeng Zhang, Peilin Zhao, Wenwu Zhu, Steven C. H. Hoi, Tong Zhang

Matrix Eigen-decomposition via Doubly Stochastic Riemannian Optimization. ICML 2016
Zhiqiang Xu, Peilin Zhao, Jianneng Cao, Xiaoli Li

Stochastic Optimization with Importance Sampling for Regularized Loss Minimization. ICML 2015
Peilin Zhao, Tong Zhang

Online Transfer Learning. Artificial Intelligence 2014
Peilin Zhao, Steven C. H. Hoi, Jialei Wang, Bin Li

Cost-sensitive online active learning with application to malicious URL detection. KDD 2013
Peilin Zhao, Steven C. H. Hoi

Fast Bounded Online Gradient Descent Algorithms for Scalable Kernel-Based Online Learning. ICML 2012
Peilin Zhao, Steven C. H. Hoi, Jialei Wang, Rong Jin, Pengcheng Wu

Online AUC Maximization. ICML 2011
Peilin Zhao, Steven C. H. Hoi, Rong Jin, Tianbao Yang

OTL: A Framework of Online Transfer Learning. ICML 2010
Peilin Zhao, Steven C. H. Hoi

DUOL: A Double Updating Approach for Online Learning. NIPS 2009
Peilin Zhao, Steven C. H. Hoi, Rong Jin



Associate Editor:

Area Chair:

Senior PC:

Best Paper Award committee: