| On the convergence of adam and beyond SJ Reddi, S Kale, S Kumar 6th International Conference on Learning Representations, 2018 | 3203 | 2018 |
| SCAFFOLD: Stochastic controlled averaging for federated learning SP Karimireddy, S Kale, M Mohri, S Reddi, S Stich, AT Suresh International Conference on Machine Learning, 5132-5143, 2020 | 3174 | 2020 |
| Logarithmic regret algorithms for online convex optimization E Hazan, A Agarwal, S Kale Machine Learning 69 (2), 169-192, 2007 | 1364 | 2007 |
| The multiplicative weights update method: A meta-algorithm and applications S Arora, E Hazan, S Kale Theory of Computing 8 (1), 121-164, 2012 | 1270 | 2012 |
| Privacy, accuracy, and consistency too: a holistic solution to contingency table release B Barak, K Chaudhuri, C Dwork, S Kale, F McSherry, K Talwar Proceedings of the twenty-sixth ACM SIGMOD-SIGACT-SIGART Symposium on …, 2007 | 624 | 2007 |
| Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits A Agarwal, D Hsu, S Kale, J Langford, L Li, RE Schapire arXiv preprint arXiv:1402.0555, 2014 | 592 | 2014 |
| Adaptive methods for nonconvex optimization M Zaheer, S Reddi, D Sachan, S Kale, S Kumar Advances in neural information processing systems 31, 2018 | 509 | 2018 |
| A Field Guide to Federated Optimization J Wang, Z Charles, Z Xu, G Joshi, HB McMahan, M Al-Shedivat, G Andrew, ... arXiv preprint arXiv:2107.06917, 2021 | 381 | 2021 |
| Efficient Optimal Learning for Contextual Bandits M Dudik, D Hsu, S Kale, N Karampatziakis, J Langford, L Reyzin, T Zhang Arxiv preprint arXiv:1106.2369, 2011 | 374 | 2011 |
| Estimating Training Data Influence by Tracing Gradient Descent G Pruthi, F Liu, S Kale, M Sundararajan Advances in Neural Information Processing Systems 33, 2020 | 362 | 2020 |
| Beyond the regret minimization barrier: optimal algorithms for stochastic strongly-convex optimization. E Hazan, S Kale Journal of Machine Learning Research 15 (1), 2489-2512, 2014 | 321 | 2014 |
| Breaking the centralized barrier for cross-device federated learning SP Karimireddy, M Jaggi, S Kale, M Mohri, S Reddi, SU Stich, AT Suresh Advances in Neural Information Processing Systems 34, 28663-28676, 2021 | 299* | 2021 |
| Algorithms for portfolio management based on the newton method A Agarwal, E Hazan, S Kale, RE Schapire Proceedings of the 23rd international conference on Machine learning, 9-16, 2006 | 290 | 2006 |
| A combinatorial, primal-dual approach to semidefinite programs S Arora, S Kale Proceedings of the thirty-ninth annual ACM symposium on Theory of computing …, 2007 | 283 | 2007 |
| Projection-free Online Learning E Hazan, S Kale Arxiv preprint arXiv:1206.4657, 2012 | 269 | 2012 |
| Who Moderates the Moderators? Crowdsourcing Abuse Detection in User-Generated Content A Ghosh, S Kale, P McAfee Proceedings of the 12th ACM conference on Electronic commerce, 167-176, 2011 | 225 | 2011 |
| Fast algorithms for approximate semidefinite programming using the multiplicative weights update method S Arora, E Hazan, S Kale 46th Annual IEEE Symposium on Foundations of Computer Science (FOCS'05), 339-348, 2005 | 193 | 2005 |
| Extracting certainty from uncertainty: Regret bounded by variation in costs E Hazan, S Kale Machine learning 80 (2-3), 165-188, 2010 | 186 | 2010 |
| Beyond the regret minimization barrier: an optimal algorithm for stochastic strongly-convex optimization E Hazan, S Kale Proceedings of the 24th Annual Conference on Learning Theory, 421-436, 2011 | 169 | 2011 |
| O(\logn) Approximation to SPARSEST CUT in ̃O(n^2) Time S Arora, E Hazan, S Kale SIAM Journal on Computing 39 (5), 1748-1771, 2010 | 138 | 2010 |
Elad HazanProfessor at Princeton University and Director Google AI PrincetonVerified email at princeton.edu