Farzan Farnia

Farzan Farnia is an assistant professor at the Department of Computer Science and Engineering, The Chinese University of Hong Kong. He received his B.Sc. degree in electrical engineering and mathematics from Sharif University of Technology and his M.Sc. and Ph.D. degrees in electrical engineering from Stanford University. 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. His research interests include machine learning, deep learning theory, optimization, and information theory. He has published extensively in top conferences and journals, including ICML, ICLR, and NeurIPS.

Farzan Farnia is an Assistant Professor at the Chinese University of Hong Kong, specializing in Machine Learning, Optimization, and Information Theory. His research focuses on advancing generative models, federated learning, and adversarial training through theoretical and algorithmic innovations. Key contributions include analyzing the stability and generalization of gradient-based minimax learners, developing spectral normalization for adversarial training, and exploring information-theoretic metrics for evaluating generative models. His work also addresses challenges in energy harvesting communication and personalized federated learning, emphasizing robustness and scalability. Farnia's research bridges theoretical foundations with practical applications in machine learning and signal processing.