Tianyi Lin
 |
Postdoctoral Associate Laboratory for Information & Decision Systems (LIDS) E-mail: darren_lin@berkeley.edu |
About Me
I am currently a Postdoctoral Associate in the Laboratory for Information & Decision Systems (LIDS) at MIT, working with Asu Ozdaglar.
I got my Ph.D. in Electrical Engineering and Computer Science at University of California, Berkeley, where I was advised by Michael I. Jordan; I was also associated with the Berkeley Artificial Intelligence Research group (BAIR) and RISELab. Prior to that, I got 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 University of California, Berkeley.
My research interests lie broadly in the span of optimization, game theory and machine learning. In particular, I have been developing methods appropriate for equilibrium computation with structured model and data, and understanding the efficiency in social learning. I am also interested in problems arising from optimal transport and large-scale text analytics.
Recent News
May. 2023: I will join Columbia University as an assistant professor in the Department of Industrial Engineering and Operations Research, starting Summer 2024!
May. 2023: The paper Deterministic Nonsmooth Nonconvex Optimization is accepted by COLT 2023.
Jan. 2023: The paper First-Order Algorithms for Nonlinear Generalized Nash Equilibrium Problems is accepted by Journal of Machine Learning Research.
Nov. 2022: The paper Monotone Inclusions, Acceleration and Closed-Loop Control is accepted by Mathematics of Operations Research.
Sep. 2022: The paper Gradient-Free Methods for Deterministic and Stochastic Nonsmooth Nonconvex Optimization is accepted by NeurIPS 2022.
Sep. 2022: The paper First-Order Algorithms for Min-Max Optimization in Geodesic Metric Spaces is accepted by NeurIPS 2022.
May. 2022: The paper On the Efficiency of Entropic Regularized Algorithms for Optimal Transport is accepted by Journal of Machine Learning Research.
May. 2022: The paper Online Nonsubmodular Minimization with Delayed Costs: From Full Information to Bandit Feedback is accepted by ICML 2022.
Mar. 2022: The paper Accelerating Adaptive Cubic Regularization of Newton's Method via Random Sampling is accepted by Journal of Machine Learning Research.
Feb. 2022: The paper On the Complexity of Approximating Multimarginal Optimal Transport is accepted by Journal of Machine Learning Research.