| Communication-efficient learning of deep networks from decentralized data HB McMahan, E Moore, D Ramage, S Hampson, B Agüera y Arcas Proceedings of the 20 th International Conference on Artificial Intelligence …, 2017 | 3237* | 2017 |
| Deep learning with differential privacy M Abadi, A Chu, I Goodfellow, HB McMahan, I Mironov, K Talwar, L Zhang Proceedings of the 2016 ACM SIGSAC conference on computer and communications …, 2016 | 2148 | 2016 |
| Federated learning: Strategies for improving communication efficiency J Konečný, HB McMahan, FX Yu, P Richtárik, AT Suresh, D Bacon arXiv preprint arXiv:1610.05492, 2016 | 1635 | 2016 |
| Practical secure aggregation for privacy-preserving machine learning K Bonawitz, V Ivanov, B Kreuter, A Marcedone, HB McMahan, S Patel, ... proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications …, 2017 | 921 | 2017 |
| Advances and open problems in federated learning P Kairouz, HB McMahan, B Avent, A Bellet, M Bennis, AN Bhagoji, ... arXiv preprint arXiv:1912.04977, 2019 | 904 | 2019 |
| Towards federated learning at scale: System design K Bonawitz, H Eichner, W Grieskamp, D Huba, A Ingerman, V Ivanov, ... arXiv preprint arXiv:1902.01046, 2019 | 824 | 2019 |
| Ad click prediction: a view from the trenches HB McMahan, G Holt, D Sculley, M Young, D Ebner, J Grady, L Nie, ... Proceedings of the 19th ACM SIGKDD international conference on Knowledge …, 2013 | 771 | 2013 |
| Federated optimization: Distributed machine learning for on-device intelligence J Konečný, HB McMahan, D Ramage, P Richtárik arXiv preprint arXiv:1610.02527, 2016 | 682 | 2016 |
| Online convex optimization in the bandit setting: gradient descent without a gradient AD Flaxman, AT Kalai, HB McMahan arXiv preprint cs/0408007, 2004 | 617 | 2004 |
| Learning differentially private recurrent language models HB McMahan, D Ramage, K Talwar, L Zhang arXiv preprint arXiv:1710.06963, 2017 | 471* | 2017 |
| Federated learning: Collaborative machine learning without centralized training data B McMahan, D Ramage Google Research Blog 3, 2017 | 318 | 2017 |
| Robust Submodular Observation Selection. A Krause, HB McMahan, C Guestrin, A Gupta Journal of Machine Learning Research 9 (12), 2008 | 285 | 2008 |
| Federated optimization: Distributed optimization beyond the datacenter J Konečný, B McMahan, D Ramage arXiv preprint arXiv:1511.03575, 2015 | 277 | 2015 |
| Leaf: A benchmark for federated settings S Caldas, SMK Duddu, P Wu, T Li, J Konečný, HB McMahan, V Smith, ... arXiv preprint arXiv:1812.01097, 2018 | 255 | 2018 |
| Planning in the presence of cost functions controlled by an adversary HB McMahan, GJ Gordon, A Blum Proceedings of the 20th International Conference on Machine Learning (ICML …, 2003 | 250 | 2003 |
| Adaptive bound optimization for online convex optimization HB McMahan, M Streeter Proceedings of the 23rd Annual Conference on Learning Theory (COLT), 2010 | 247 | 2010 |
| cpSGD: Communication-efficient and differentially-private distributed SGD N Agarwal, AT Suresh, F Yu, S Kumar, HB Mcmahan arXiv preprint arXiv:1805.10559, 2018 | 197 | 2018 |
| Follow-the-regularized-leader and mirror descent: Equivalence theorems and l1 regularization HB McMahan Proceedings of the 14th International Conference on Artificial Intelligence …, 2011 | 190 | 2011 |
| Bounded real-time dynamic programming: RTDP with monotone upper bounds and performance guarantees HB McMahan, M Likhachev, GJ Gordon Proceedings of the 22nd international conference on Machine learning, 569-576, 2005 | 183 | 2005 |
| Distributed mean estimation with limited communication AT Suresh, XY Felix, S Kumar, HB McMahan International Conference on Machine Learning, 3329-3337, 2017 | 163 | 2017 |
Daniel RamageGoogle ResearchVerified email at google.com
