Publications and Preprints

Preprints

• Farzan Farnia*, William Wang*, Subhro Das, Ali Jadbabaie, “GAT-GMM: Generative Adversarial Training for Gaussian Mixture Models”, arXiv:2006.10293 [Preprint]
  

• Farzan Farnia, Amirali Aghazadeh, James Zou, David Tse, “Group-Structured Adversarial Training”, [Preprint]

Published Papers

• Farzan Farnia, Asu Ozdaglar, “Train simultaneously, generalize better: Stability of gradient-based minimax learners”, International Conference on Machine Learning (ICML) 2021 [Paper]
  

• Theo Diamandis*, Yonina Eldar*, Alireza Fallah*, Farzan Farnia*, Asu Ozdaglar*, “A Wasserstein Minimax Framework to Mixed Linear Regression”, International Conference on Machine Learning (ICML) 2021, [Paper]
  

• Amirhossein Reisizadeh*, Farzan Farnia*, Ramtin Pedarsani, Ali Jadbabaie, ”Robust Federated Learning: The Case of Affine Distribution Shifts”, Neural Information Processing Systems (NeurIPS) 2020, [Paper][Poster]
  

• Farzan Farnia, Asu Ozdaglar, ”Do GANs always have Nash equilibria?”, International Conference on Machine Learning (ICML) 2020, [Paper][Video]
  

• 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, April 2020, [Paper][Slides]

• Farzan Farnia, Jesse M. Zhang, David Tse, ”A Fourier-Based Approach to Generalization and Optimization in Deep Learning”, IEEE Journal on Selected Areas in Information Theory, May 2020, [Paper]

• Farzan Farnia*, Jesse M. Zhang*, David Tse, ”Generalizable Adversarial Training via Spectral Normalization”, International Conference on Learning Representations (ICLR) 2019, [Paper][Poster]

• Farzan Farnia, David Tse, ”A Convex Duality Framework for GANs”, Neural Information Processing Systems (NeurIPS) 2018, [Paper][Poster][Video]

• Farzan Farnia, David Tse, ”A Minimax Approach to Supervised Learning”, Neural Information Processing Systems (NeurIPS) 2018, [Paper][Poster]
  

• Meisam Razaviyayn, Farzan Farnia, David Tse, ”Discrete Rényi Classifiers”, Neural Information Processing Systems (NeurIPS) 2015, [Paper][Poster]
  

• Farzan Farnia, Meisam Razaviyayn, Sreeram Kannan, David Tse, ”Minimum HGR correlation principle: From marginals to joint distribution”, IEEE International Symposium on Information Theory (ISIT) 2015, [Paper]

• Bobbie Chern, Farzan Farnia, Ayfer Özgür, ”On Feedback in Gaussian Multihop Networks”, IEEE Transactions on Information Theory, July 2015, [Paper]

• Yishun Dong, Farzan Farnia, Ayfer Özgür, ”On Feedback in Gaussian Multihop Networks”, IEEE Journal on Selected Areas in Communications, March 2015, [Paper]

• Farzan Farnia, Ayfer Özgür, ”On feedback in Gaussian multi-hop networks”, Information Theory and Applications Workshop (ITA) 2014, [Paper]

• Farzan Farnia, S. Jamaloddin Golestani, ”Asymptotic behavior of network capacity under spatial network coding”, IEEE Wireless Communications and Networking Conference (WCNC) 2013, [Paper]

*: Equal Contribution