Audra McMillan
Audra McMillan
Verified email at - Homepage
Cited by
Cited by
Hiding among the clones: A simple and nearly optimal analysis of privacy amplification by shuffling
V Feldman, A McMillan, K Talwar
2021 IEEE 62nd Annual Symposium on Foundations of Computer Science (FOCS …, 2022
The structure of optimal private tests for simple hypotheses
CL Canonne, G Kamath, A McMillan, A Smith, J Ullman
Proceedings of the 51st Annual ACM SIGACT Symposium on Theory of Computing …, 2019
Differentially private simple linear regression
D Alabi, A McMillan, J Sarathy, A Smith, S Vadhan
arXiv preprint arXiv:2007.05157, 2020
Private identity testing for high-dimensional distributions
CL Canonne, G Kamath, A McMillan, J Ullman, L Zakynthinou
Advances in neural information processing systems 33, 10099-10111, 2020
A cross sectional study of water quality from dental unit water lines in dental practices in the West of Scotland
AJ Smith, S McHugh, L McCormick, R Stansfield, A McMillan, J Hood
British dental journal 193 (11), 645-648, 2002
Stronger privacy amplification by shuffling for rényi and approximate differential privacy
V Feldman, A McMillan, K Talwar
Proceedings of the 2023 Annual ACM-SIAM Symposium on Discrete Algorithms …, 2023
Property testing for differential privacy
AC Gilbert, A McMillan
2018 56th Annual Allerton Conference on Communication, Control, and …, 2018
Mean estimation with user-level privacy under data heterogeneity
R Cummings, V Feldman, A McMillan, K Talwar
Advances in Neural Information Processing Systems 35, 29139-29151, 2022
Online learning via the differential privacy lens
JD Abernethy, YH Jung, C Lee, A McMillan, A Tewari
Advances in Neural Information Processing Systems 32, 2019
Nonparametric differentially private confidence intervals for the median
J Drechsler, I Globus-Harris, A Mcmillan, J Sarathy, A Smith
Journal of Survey Statistics and Methodology 10 (3), 804-829, 2022
Online learning via differential privacy
J Abernethy, C Lee, A McMillan, A Tewari
arXiv preprint arXiv:1711.10019, 2017
Local differential privacy for physical sensor data and sparse recovery
A McMillan, AC Gilbert
2018 52nd Annual Conference on Information Sciences and Systems (CISS), 1-6, 2018
Instance-optimal differentially private estimation
A McMillan, A Smith, J Ullman
arXiv preprint arXiv:2210.15819, 2022
Samplable anonymous aggregation for private federated data analysis
K Talwar, S Wang, A McMillan, V Jina, V Feldman, B Basile, A Cahill, ...
arXiv preprint arXiv:2307.15017, 2023
Controlling privacy loss in sampling schemes: An analysis of stratified and cluster sampling
M Bun, J Drechsler, M Gaboardi, A McMillan, J Sarathy
arXiv preprint arXiv:2007.12674, 2020
Private federated statistics in an interactive setting
A McMillan, O Javidbakht, K Talwar, E Briggs, M Chatzidakis, J Chen, ...
arXiv preprint arXiv:2211.10082, 2022
When is non-trivial estimation possible for graphons and stochastic block models?
A McMillan, A Smith
Information and Inference: A Journal of the IMA 7 (2), 169-181, 2018
Differentially Private Heavy Hitters using Federated Analytics
K Chadha, J Chen, J Duchi, V Feldman, H Hashemi, O Javidbakht, ...
Federated Learning and Analytics in Practice: Algorithms, Systems …, 0
Total positivity of a shuffle matrix
A McMillan
Involve, a Journal of Mathematics 5 (1), 61-65, 2012
Differential Privacy, Property Testing, and Perturbations
A McMillan
The system can't perform the operation now. Try again later.
Articles 1–20