Assistant Professor
Machine Learning, Optimization, Information Theory
Biography
Farzan Farnia is an assistant professor at the Department of Computer Science and Engineering at the Chinese University of Hong Kong. Prior to joining CUHK, he was a postdoctoral research associate at the Laboratory for Information and Decision Systems, Massachusetts Institute of Technology, from 2019-2021. He received his M.Sc. and Ph.D. degrees in electrical engineering from Stanford University and his B.Sc. degree in electrical engineering and mathematics from Sharif University of Technology. At Stanford, he was a graduate research assistant at the Information Systems Laboratory advised by David Tse. Farzan’s research interests include machine learning, deep learning theory, optimization, and information theory. He has been the recipient of a Stanford Graduate Fellowship from 2013-2016 and the Numerical Technology Founders Prize as the second top performer of Stanford Electrical Engineering Ph.D. Qualifying Exams in 2014.
- Farzan Farnia, Asuman Ozdaglar: Do GANs always have Nash equilibria? ICML 2020
- Farzan Farnia, Jesse Zhang, David Tse: Generalizable Adversarial Training via Spectral Normalization. ICLR 2019
- Soheil Feizi, Farzan Farnia, Tony Ginart, David Tse: Understanding GANs in the LQG setting: Formulation, Generalization and Stability. IEEE Journal on Selected Areas in Information Theory 2020
- Farzan Farnia, David Tse: A Convex Duality Framework for GANs. NeurIPS 2018
- Farzan Farnia, David Tse: A Minimax Approach to Supervised Learning. NeurIPS 2016
- Farzan Farnia, Amirhossein Reisizadeh, Ramtin Pedarsani, Ali Jadbabaie: An Optimal Transport Approach to Federated Learning. JSAIT 2022
- Haochuan Li, Farzan Farnia, Subhro Das, Ali Jadbabaie: On Convergence of Gradient Descent Ascent: A Tight Local Analysis. ICML 2022
- Farzan Farnia, Asuman Ozdaglar: Train simultaneously, generalize better: Stability of gradient-based minimax learners. ICML 2021
- Amirhossein Reisizadeh, Farzan Farnia, Ramtin Pedarsani, Ali Jadbabaie: Robust Federated Learning: The Case of Affine Distribution Shifts. NeurIPS 2020
- Farzan Farnia, William Wang, Subhro Das, Ali Jadbabaie: GAT-GMM: Generative Adversarial Training for Gaussian Mixture Models.
- Awarded Numerical Technology Founders Prize, 2014
- Second Top Performer of Stanford Electrical Engineering Ph.D. Qualifying Exams, 2014
- Awarded Stanford Graduate Fellowship, 2013