Tianyi Lin works at the intersection of game theory, machine learning, optimization and networks. He has been developing efficient methods for (i) game-theoretic learning with strategic agents and (ii) data-driven learning with real data. His research has found applications in areas such as data mining (e.g. topic modeling in social media), operation management (e.g. online inventory control), and financial risk management (e.g. optimization with uncertainty). His recent work focused on two directions: (i) large-scale equilibrium computation and (ii) economics of artificial intelligence (AI). Notably, he has built on the social learning models by considering whether the advanced technological toolbox (e.g., ChatGPT) can nudge the consensus belief closer to the truth.
Tianyi obtained his Ph.D. from UC Berkeley in 2023 and was associated with the BAIR group. Before joining Columbia, he spent one year as a Postdoctoral Associate at the Laboratory for Information & Decision Systems (LIDS) at MIT. Prior to that, he 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.
