| Fedpaq: A communication-efficient federated learning method with periodic averaging and quantization A Reisizadeh, A Mokhtari, H Hassani, A Jadbabaie, R Pedarsani International Conference on Artificial Intelligence and Statistics, 2021-2031, 2020 | 479 | 2020 |
| Efficient and accurate estimation of lipschitz constants for deep neural networks M Fazlyab, A Robey, H Hassani, M Morari, G Pappas Advances in Neural Information Processing Systems 32, 2019 | 315 | 2019 |
| Exploiting shared representations for personalized federated learning L Collins, H Hassani, A Mokhtari, S Shakkottai International Conference on Machine Learning, 2089-2099, 2021 | 203 | 2021 |
| Finite-length scaling of polar codes SH Hassani, K Alishahi, R Urbanke arXiv preprint arXiv:1304.4778, 2013 | 177* | 2013 |
| Fast and provably good seedings for k-means O Bachem, M Lucic, H Hassani, A Krause Advances in neural information processing systems 29, 2016 | 160 | 2016 |
| Approximate k-means++ in sublinear time O Bachem, M Lucic, SH Hassani, A Krause Proceedings of the AAAI conference on artificial intelligence 30 (1), 2016 | 141 | 2016 |
| On the construction of polar codes R Pedarsani, SH Hassani, I Tal, E Telatar Information Theory Proceedings (ISIT), 2011 IEEE International Symposium on …, 2011 | 139 | 2011 |
| Unified scaling of polar codes: Error exponent, scaling exponent, moderate deviations, and error floors M Mondelli, SH Hassani, RL Urbanke IEEE Transactions on Information Theory 62 (12), 6698-6712, 2016 | 131 | 2016 |
| From polar to Reed-Muller codes: A technique to improve the finite-length performance M Mondelli, SH Hassani, RL Urbanke IEEE Transactions on Communications 62 (9), 3084-3091, 2014 | 126 | 2014 |
| An exact quantized decentralized gradient descent algorithm A Reisizadeh, A Mokhtari, H Hassani, R Pedarsani IEEE Transactions on Signal Processing 67 (19), 4934-4947, 2019 | 124* | 2019 |
| Growing a graph matching from a handful of seeds E Kazemi, SH Hassani, M Grossglauser Proceedings of the VLDB Endowment 8 (10), 1010-1021, 2015 | 122 | 2015 |
| Gradient methods for submodular maximization H Hassani, M Soltanolkotabi, A Karbasi Advances in Neural Information Processing Systems 30, 2017 | 112 | 2017 |
| Universal polar codes SH Hassani, R Urbanke 2014 IEEE International Symposium on Information Theory, 1451-1455, 2014 | 101 | 2014 |
| Stochastic conditional gradient methods: From convex minimization to submodular maximization A Mokhtari, H Hassani, A Karbasi The Journal of Machine Learning Research 21 (1), 4232-4280, 2020 | 100 | 2020 |
| How to achieve the capacity of asymmetric channels M Mondelli, R Urbanke, SH Hassani 2014 52nd Annual Allerton Conference on Communication, Control, and …, 2014 | 92* | 2014 |
| Age of information in random access channels X Chen, K Gatsis, H Hassani, SS Bidokhti IEEE Transactions on Information Theory 68 (10), 6548-6568, 2022 | 90 | 2022 |
| Achieving Marton’s region for broadcast channels using polar codes M Mondelli, SH Hassani, I Sason, RL Urbanke IEEE Transactions on Information Theory 61 (2), 783-800, 2014 | 90 | 2014 |
| Robust and communication-efficient collaborative learning A Reisizadeh, H Taheri, A Mokhtari, H Hassani, R Pedarsani Advances in Neural Information Processing Systems 32, 2019 | 83 | 2019 |
| Linear convergence in federated learning: Tackling client heterogeneity and sparse gradients A Mitra, R Jaafar, GJ Pappas, H Hassani Advances in Neural Information Processing Systems 34, 14606-14619, 2021 | 81* | 2021 |
| Precise tradeoffs in adversarial training for linear regression A Javanmard, M Soltanolkotabi, H Hassani Conference on Learning Theory, 2034-2078, 2020 | 76 | 2020 |
Ruediger UrbankeEPFLVerified email at epfl.ch
