Farzan Farnia


Office #918,
Ho Sin-Hang Engineering Building,
The Chinese University of Hong Kong,
Shatin N.T. Hong Kong

Email: farnia AT cse.cuhk.edu.hk
[Google Scholar] [LinkedIn]

About Me

I am an Assistant Professor of Computer Science and Engineering at The Chinese University of Hong Kong. Prior to joining CUHK, I was a postdoctoral research associate at the Laboratory for Information & Decision Systems, Massachusetts Institute of Technology, from 2019-2021. I received my M.Sc. and Ph.D. degrees in Electrical Engineering from Stanford University where I was a graduate research assistant at the Information Systems Laboratory advised by David Tse. I also received my B.Sc. degree in Electrical Engineering and Mathematics from Sharif University of Technology.

My research interests lie in learning and information sciences with a particular focus on multi-learner learning frameworks where I study the convergence, equilibrium, and robustness properties of multi-learner learning algorithms. For more details regarding my research, please visit the Research page. For a complete list of my publications and preprints, please visit the Publications page.

Selected Papers

F. Farnia, A. Ozdaglar, “Train simultaneously, generalize better: Stability of gradient-based minimax learners”, ICML 2021

A. Reisizadeh*, F. Farnia*, R. Pedarsani, A. Jadbabaie, ”Robust Federated Learning: The Case of Affine Distribution Shifts”, NeurIPS 2020

F. Farnia, A. Ozdaglar, “Do GANs always have Nash equilibria?”, ICML 2020

F. Farnia, D. Tse, “A Convex Duality Framework for GANs”, NeurIPS 2018

F. Farnia, D. Tse, “A Minimax Approach to Supervised Learning”, NeurIPS 2016