Tianyi Lin

prof_pic.jpg

Welcome to my homepage!

I am an assistant professor in the Department of Industrial Engineering and Operations Research (IEOR) at Columbia University. My research interests lie in optimization and machine learning, game theory, social and economic network, and optimal transport.

I obtained my Ph.D. in Electrical Engineering and Computer Science at UC Berkeley, where I was advised by Professor Michael I. Jordan and was associated with the Berkeley Artificial Intelligence Research (BAIR) group. From 2023 to 2024, I was a postdoctoral researcher at the Laboratory for Information & Decision Systems (LIDS) at Massachusetts Institute of Technology, working with Professor Asuman Ozdaglar. Prior to that, I received a B.S. in Mathematics from Nanjing University, a M.S. in Pure Mathematics and Statistics from University of Cambridge and a M.S. in Operations Research from UC Berkeley.

Email: tl3335 [at] columbia [dot] edu

Office: 535B Mudd Building, 500 West 120th Street, New York, NY 10027

Prospective students: I am unable to respond to most inquiries regarding openings for graduate and postdoctoral positions in my group. Admissions to Columbia University are handled at a department-wide level, not by me individually. If you have been admitted to Columbia University, please feel free to contact me.


news

May 20, 2025 The new paper, Spectral policy optimization: Coloring your incorrect reasoning in GRPO, coauthored with Peter Chen, Xiaopeng Li, Ziniu Li and Xi Chen was posted to ArXiv.
May 09, 2025 The new paper, ComPO: Preference alignment via comparison oracles, coauthored with Peter Chen, Xi Chen and Wotao Yin was posted to ArXiv.
Jan 27, 2025 The paper, Two-timescale gradient descent ascent algorithms for nonconvex minimax optimization, coauthored with Chi Jin and Michael. I. Jordan was accepted to Journal of Machine Learning Research.

selected publications

  1. Spectral policy optimization: Coloring your incorrect reasoning in GRPO
    Peter Chen, Xiaopeng Li, Ziniu Li, Xi Chen, and Tianyi Lin
    ArXiv Preprint, 2025
  2. ComPO: Preference alignment via comparison oracles
    Peter Chen, Xi Chen, Wotao Yin, and Tianyi Lin
    ArXiv Preprint, 2025
  3. Two-timescale gradient descent ascent algorithms for nonconvex minimax optimization
    Tianyi Lin, Chi Jin, and Michael I Jordan
    Journal of Machine Learning Research, 2025