| Protection against reconstruction and its applications in private federated learning A Bhowmick, J Duchi, J Freudiger, G Kapoor, R Rogers arXiv preprint arXiv:1812.00984, 2018 | 529 | 2018 |
| Differentially private chi-squared hypothesis testing: Goodness of fit and independence testing M Gaboardi, H Lim, R Rogers, S Vadhan International conference on machine learning, 2111-2120, 2016 | 196 | 2016 |
| Learning with Privacy at Scale DP Team Apple Machine Learning Journal 1 (8), 2017 | 142 | 2017 |
| Privacy odometers and filters: Pay-as-you-go composition RM Rogers, A Roth, J Ullman, S Vadhan Advances in Neural Information Processing Systems, 1921-1929, 2016 | 140 | 2016 |
| Lower bounds for locally private estimation via communication complexity J Duchi, R Rogers Conference on Learning Theory, 1161-1191, 2019 | 131 | 2019 |
| Linkedin's audience engagements api: A privacy preserving data analytics system at scale R Rogers, S Subramaniam, S Peng, D Durfee, S Lee, SK Kancha, ... arXiv preprint arXiv:2002.05839, 2020 | 124 | 2020 |
| Practical differentially private top-k selection with pay-what-you-get composition D Durfee, RM Rogers Advances in Neural Information Processing Systems 32, 2019 | 120 | 2019 |
| Psi M Gaboardi, J Honaker, G King, J Murtagh, K Nissim, J Ullman, S Vadhan, ... arXiv preprint arXiv:1609.04340, 2016 | 110 | 2016 |
| Privatized machine learning using generative adversarial networks A Bhowmick, AH Vyrros, RM Rogers US Patent App. 15/892,246, 2019 | 109 | 2019 |
| Max-information, differential privacy, and post-selection hypothesis testing R Rogers, A Roth, A Smith, O Thakkar 2016 IEEE 57th Annual Symposium on Foundations of Computer Science (FOCS …, 2016 | 101 | 2016 |
| Local private hypothesis testing: Chi-square tests M Gaboardi, R Rogers International Conference on Machine Learning, 1626-1635, 2018 | 83 | 2018 |
| Optimal differential privacy composition for exponential mechanisms J Dong, D Durfee, R Rogers International Conference on Machine Learning, 2597-2606, 2020 | 82 | 2020 |
| Locally Private Mean Estimation: -test and Tight Confidence Intervals M Gaboardi, R Rogers, O Sheffet The 22nd international conference on artificial intelligence and statistics …, 2019 | 70 | 2019 |
| Advancing differential privacy: Where we are now and future directions for real-world deployment R Cummings, D Desfontaines, D Evans, R Geambasu, Y Huang, ... arXiv preprint arXiv:2304.06929, 2023 | 65 | 2023 |
| Fully-adaptive composition in differential privacy J Whitehouse, A Ramdas, R Rogers, S Wu International conference on machine learning, 36990-37007, 2023 | 59 | 2023 |
| Distributed labeling for supervised learning A Bhowmick, RM Rogers, US Vaishampayan, AH Vyrros US Patent 11,710,035, 2023 | 55 | 2023 |
| Asymptotically truthful equilibrium selection in large congestion games RM Rogers, A Roth Proceedings of the fifteenth ACM conference on Economics and computation …, 2014 | 55 | 2014 |
| Bounding, concentrating, and truncating: Unifying privacy loss composition for data analytics M Cesar, R Rogers Algorithmic Learning Theory, 421-457, 2021 | 51 | 2021 |
| Differentially private histograms under continual observation: Streaming selection into the unknown AR Cardoso, R Rogers International Conference on Artificial Intelligence and Statistics, 2397-2419, 2022 | 48 | 2022 |
| Do prices coordinate markets? J Hsu, J Morgenstern, R Rogers, A Roth, R Vohra Proceedings of the forty-eighth annual ACM symposium on Theory of Computing …, 2016 | 45 | 2016 |
Aaron RothProfessor of Computer Science, University of PennsylvaniaVerified email at cis.upenn.edu
