LIN, Tao

Assistant Professor

Education Background

Ph.D. in Computer Science, Harvard University (2020-2025)

B.Sc. in Computer Science and Technology, Peking University (2016-2020)

Academic Area
Artificial Intelligence, Computer Science, Machine Learning and Artificial Intelligence, Operations Research, Optimization
Research Field
Economics and Computation, Mechanism Design, Information Design, Algorithmic Game Theory, Machine Learning, Theoretical Computer Science
Personal Website
https://tao-l.github.io/
Email
lintao@cuhk.edu.cn
Biography

Tao Lin is a tenure-track assistant professor in the School of Data Science, The Chinese University of Hong Kong, Shenzhen. He received his Ph.D. in Computer Science from Harvard University (2025), and B.Sc. from Peking University (2020). Prior to joining CUHK-Shenzhen, he was a postdoctoral researcher at Microsoft Research (2025–2026).

Tao’s research spans economics, machine learning, and theoretical computer science, focusing on mechanism design and information design for learning-based decision-makers, with applications to, e.g., advertising auctions and recommender systems. His work is published on top-tier computer science conferences and economic journals. Industrial collaborations at ByteDance, Google, and Microsoft inform his research. He is a recipient of the 2025 Siebel Scholar Award.

Academic Publications

A. Representative Conference Publications

1. “Generalized Principal-Agent Problem with a Learning Agent”, International Conference on Learning Representations (ICLR), 2025 (with Yiling Chen).

2. “Information Design with Unknown Prior”, Proceedings of Innovations in Theoretical Computer Science (ITCS), 2025 (with Ce Li).

3. “Nash Convergence of Mean-Based Learning Algorithms in First Price Auctions”, Proceedings of the ACM Web Conference (WWW), 2022 (with Xiaotie Deng, Xinyan Hu, Weiqiang Zheng).

4. “User-Creator Feature Polarization in Recommender Systems with Dual Influence”, Advances in Neural Information Processing Systems (NeurIPS), 2024 (with Kun Jin, Andrew Estornell, Xiaoying Zhang, Yiling Chen, Yang Liu).

5. “Multi-Sender Persuasion: A Computational Perspective”, International Conference on Machine Learning (ICML), 2024 (with Safwan Hossain, Tonghan Wang, Yiling Chen, David C. Parkes, Haifeng Xu).

6. “Sample Complexity of Forecast Aggregation”, Advances in Neural Information Processing Systems (NeurIPS), 2023 (with Yiling Chen).

7. “Learning Utilities and Equilibria in Non-Truthful Auctions”, Advances in Neural Information Processing Systems (NeurIPS), 2020 (with Hu Fu).

 

B. Representative Journal Publications

1. “From monopoly to competition: When do optimal contests prevail?”, Games and Economic Behavior, 2025 (with Xiaotie Deng, Yotam Gafni, Ron Lavi, and Hongyi Ling).

More publications are listed on my Google Scholar page.