Tao Lin

PhD student in Computer Science

Harvard University

Biography

I am a fifth-year PhD student in Computer Science at Harvard University, where I am very fortunate to be advised by Prof. Yiling Chen. My research interest lies in the intersection between economics and machine learning. I have been working on “mechanism design + machine learning” since my undergraduate study at Peking University, working with Prof. Xiaotie Deng. Recently, I focused more on information design problems, like Bayesian persuasion and information aggregation. I am particularly interested in the interplay between economic incentives and machine learning in multi-agent systems.

Interests

Mechanism Design
Information Design
Machine Learning

Education

BSc in EECS, 2020

Peking University

Experience

Student Researcher

Google Research

Jun 2024 – Aug 2024

Hosted by Christopher Liaw.

Research Intern

ByteDance

May 2023 – Sep 2023

Hosted by Yang Liu.

Summer Research Visit

University of British Columbia

Jun 2019 – Sep 2019

Hosted by Hu Fu.

Undergraduate Research Assistant

Center on Frontiers of Computing Studies, Peking University

Sep 2018 – May 2020

Advised by Xiaotie Deng.

Working Papers

*: alphabetical or random order.

Tao Lin, Yiling Chen (2024). Generalized Principal-Agent Problem with a Learning Agent. Working paper.

Tao Lin, Ce Li (2024). Information Design with Unknown Prior. Working paper.

Publications

*: alphabetical or random order.

Tao Lin, Kun Jin, Andrew Estornell, Xiaoying Zhang, Yiling Chen, Yang Liu (2024). User-Creator Feature Dynamics in Recommender Systems with Dual Influence. NeurIPS.

Yiling Chen*, Tao Lin*, Ariel D. Procaccia*, Aaditya Ramdas*, Itai Shapira* (2024). Bias Detection Via Signaling. NeurIPS.

Safwan Hossain*, Tonghan Wang*, Tao Lin*, Yiling Chen, David Parkes, Haifeng Xu (2024). Multi-Sender Persuasion: A Computational Perspective. ICML.

Jiahao Zhang, Tao Lin, Weiqiang Zheng, Zhe Feng, Yifeng Teng, Xiaotie Deng (2024). Learning Thresholds with Latent Values and Censored Feedback. ICLR.

Tao Lin, Yiling Chen (2023). Sample Complexity of Forecast Aggregation. NeurIPS (spotlight).

PDF Poster arXiv

Xiaotie Deng*, Yotam Gafni*, Ron Lavi*, Tao Lin*, Hongyi Ling* (2023). From Monopoly to Competition: Optimal Contests Prevail. AAAI.

PDF Poster arXiv

Xiaotie Deng*, Xinyan Hu*, Tao Lin*, Weiqiang Zheng* (2022). Nash Convergence of Mean-Based Learning Algorithms in First Price Auctions. The Web Conference (WWW).

PDF DOI arXiv slides 15-min video 2-min video by Xinyan

Manon Revel, Tao Lin, Daniel Halpern (2022). How Many Representatives Do We Need? The Optimal Size of an Epistemic Congress. AAAI.

DOI arXiv video

Xiaotie Deng*, Ron Lavi*, Tao Lin*, Qi Qi*, Wenwei Wang*, Xiang Yan* (2020). A Game-Theoretic Analysis of the Empirical Revenue Maximization Algorithm with Endogenous Sampling. NeurIPS.

PDF arXiv slides publisher site

Hu Fu*, Tao Lin* (2020). Learning Utilities and Equilibria in Non-Truthful Auctions. NeurIPS.

PDF arXiv publisher site

Xiaotie Deng*, Tao Lin*, Tao Xiao* (2020). Private Data Manipulation in Optimal Sponsored Search Auction. The Web Conference (WWW).

Notes (not intended to publish)

Yiling Chen*, Tao Lin* (2023). Persuading a Behavioral Agent: Approximately Best Responding and Learning. Draft.

Tao Lin (2022). How Does Independence Help Generalization? Sample Complexity of ERM on Product Distributions. Note.

Xiaoming Li*, Tao Lin* (2019). On Clearing Prices in Matching Markets: A Simple Characterization without Duality. Note.

Recent Talks

Bayesian Persuasion with a Learning Agent

Oct 20, 2024 INFORMS Annual Meeting

Generalized Principal-Agent Problem with a Learning Agent

Oct 10, 2024 ESIF Economics and AI+ML Meeting

Private Data Manipulation in Sponsored Search Auctions

Aug 17, 2023 Invited talk at CCF Annual Conference on Computational Economics

Sample Complexity of Forecast Aggregation

Jun 14, 2023 Peking University Turing Class "CS peer talk"

Persuading a Behavioral Agent: Approximately Best Responding and Learning

Mar 3, 2023 Harvard EconCS seminar