| Gans may have no nash equilibria F Farnia, A Ozdaglar arXiv preprint arXiv:2002.09124, 2020 | 174* | 2020 |
| Generalizable adversarial training via spectral normalization F Farnia, JM Zhang, D Tse arXiv preprint arXiv:1811.07457, 2018 | 165 | 2018 |
| Robust federated learning: The case of affine distribution shifts A Reisizadeh, F Farnia, R Pedarsani, A Jadbabaie Advances in Neural Information Processing Systems 33, 21554-21565, 2020 | 160 | 2020 |
| A minimax approach to supervised learning F Farnia, D Tse Advances in Neural Information Processing Systems 29, 2016 | 136 | 2016 |
| Understanding GANs in the LQG setting: Formulation, generalization and stability S Feizi, F Farnia, T Ginart, D Tse IEEE Journal on Selected Areas in Information Theory 1 (1), 304-311, 2020 | 111* | 2020 |
| Near optimal energy control and approximate capacity of energy harvesting communication Y Dong, F Farnia, A Özgür IEEE Journal on Selected Areas in Communications 33 (3), 540-557, 2015 | 93 | 2015 |
| A convex duality framework for GANs F Farnia, D Tse Advances in neural information processing systems 31, 2018 | 70 | 2018 |
| Train simultaneously, generalize better: Stability of gradient-based minimax learners F Farnia, A Ozdaglar International Conference on Machine Learning, 3174-3185, 2021 | 45 | 2021 |
| An optimal transport approach to personalized federated learning F Farnia, A Reisizadeh, R Pedarsani, A Jadbabaie IEEE Journal on Selected Areas in Information Theory 3 (2), 162-171, 2022 | 13 | 2022 |
| Discrete rényi classifiers M Razaviyayn, F Farnia, D Tse Advances in Neural Information Processing Systems 28, 2015 | 12 | 2015 |
| Mode-seeking divergences: theory and applications to GANs CT Li, F Farnia International Conference on Artificial Intelligence and Statistics, 8321-8350, 2023 | 10 | 2023 |
| Gat–gmm: Generative adversarial training for gaussian mixture models F Farnia, WW Wang, S Das, A Jadbabaie SIAM Journal on Mathematics of Data Science 5 (1), 122-146, 2023 | 10 | 2023 |
| Diffpattern: Layout pattern generation via discrete diffusion Z Wang, Y Shen, W Zhao, Y Bai, G Chen, F Farnia, B Yu 2023 60th ACM/IEEE Design Automation Conference (DAC), 1-6, 2023 | 9 | 2023 |
| On the role of generalization in transferability of adversarial examples Y Wang, F Farnia Uncertainty in Artificial Intelligence, 2259-2270, 2023 | 8 | 2023 |
| A Wasserstein minimax framework for mixed linear regression T Diamandis, Y Eldar, A Fallah, F Farnia, A Ozdaglar International Conference on Machine Learning, 2697-2706, 2021 | 7 | 2021 |
| A Fourier-based approach to generalization and optimization in deep learning F Farnia, JM Zhang, NT David IEEE Journal on Selected Areas in Information Theory 1 (1), 145-156, 2020 | 6 | 2020 |
| On convergence of gradient descent ascent: A tight local analysis H Li, F Farnia, S Das, A Jadbabaie International Conference on Machine Learning, 12717-12740, 2022 | 5 | 2022 |
| Minimum HGR correlation principle: From marginals to joint distribution F Farnia, M Razaviyayn, S Kannan, D Tse 2015 IEEE International Symposium on Information Theory (ISIT), 1377-1381, 2015 | 4 | 2015 |
| Provably efficient cvar rl in low-rank mdps Y Zhao, W Zhan, X Hu, H Leung, F Farnia, W Sun, JD Lee arXiv preprint arXiv:2311.11965, 2023 | 3 | 2023 |
| Interpretation of neural networks is susceptible to universal adversarial perturbations HE Oskouie, F Farnia ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023 | 3 | 2023 |
David TseThomas Kailath and Guanghan Xu Professor, Stanford UniversityVerified email at stanford.edu
