Om Thakkar
Om Thakkar
Research Software Engineer, Google
Verified email at - Homepage
Cited by
Cited by
Max-information, differential privacy, and post-selection hypothesis testing
R Rogers, A Roth, A Smith, O Thakkar
IEEE Symposium on Foundations of Computer Science 2016, 2016
Towards Practical Differentially Private Convex Optimization
R Iyengar, JP Near, D Song, O Thakkar, A Thakurta, L Wang
IEEE Symposium on Security and Privacy 2019, 2019
Model-Agnostic Private Learning
R Bassily, O Thakkar, A Thakurta
Neural Information Processing Systems 2018, 2018
Differentially private learning with adaptive clipping
O Thakkar, G Andrew, HB McMahan
arXiv preprint arXiv:1905.03871, 2019
Differentially Private Matrix Completion, Revisited
P Jain, O Thakkar, A Thakurta
International Conference on Machine Learning 2018, 2018
Characterizing private clipped gradient descent on convex generalized linear problems
S Song, O Thakkar, A Thakurta
arXiv preprint arXiv:2006.06783, 2020
Guaranteed validity for empirical approaches to adaptive data analysis
R Rogers, A Roth, A Smith, N Srebro, O Thakkar, B Woodworth
International Conference on Artificial Intelligence and Statistics, 2830-2840, 2020
Privacy amplification via random check-ins
B Balle, P Kairouz, B McMahan, OD Thakkar, A Thakurta
Advances in Neural Information Processing Systems 33, 2020
Understanding unintended memorization in federated learning
O Thakkar, S Ramaswamy, R Mathews, F Beaufays
arXiv preprint arXiv:2006.07490, 2020
Advances in Privacy-Preserving Machine Learning
O Thakkar
Boston University, 2019
Training Production Language Models without Memorizing User Data
S Ramaswamy, O Thakkar, R Mathews, G Andrew, HB McMahan, ...
arXiv preprint arXiv:2009.10031, 2020
The system can't perform the operation now. Try again later.
Articles 1–11