2024
Differentially Private Stream Processing at Scale.
Proc. VLDB Endow., August, 2024
Hash-Prune-Invert: Improved Differentially Private Heavy-Hitter Detection in the Two-Server Model.
IACR Cryptol. ePrint Arch., 2024
Near Exact Privacy Amplification for Matrix Mechanisms.
CoRR, 2024
The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD.
CoRR, 2024
Avoiding Pitfalls for Privacy Accounting of Subsampled Mechanisms under Composition.
CoRR, 2024
Efficient and Near-Optimal Noise Generation for Streaming Differential Privacy.
CoRR, 2024
Private Geometric Median.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
Differentially Private Medians and Interior Points for Non-Pathological Data.
Proceedings of the 15th Innovations in Theoretical Computer Science Conference, 2024
Stealing part of a production language model.
,
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the Forty-first International Conference on Machine Learning, 2024
Privacy Amplification for Matrix Mechanisms.
Proceedings of the Twelfth International Conference on Learning Representations, 2024
Correlated Noise Provably Beats Independent Noise for Differentially Private Learning.
Proceedings of the Twelfth International Conference on Learning Representations, 2024
2023
Differentially Private Stream Processing at Scale.
CoRR, 2023
A Bias-Variance-Privacy Trilemma for Statistical Estimation.
CoRR, 2023
Tight Auditing of Differentially Private Machine Learning.
Proceedings of the 32nd USENIX Security Symposium, 2023
Faster Differentially Private Convex Optimization via Second-Order Methods.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
Privacy Auditing with One (1) Training Run.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
Counting Distinct Elements Under Person-Level Differential Privacy.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
Algorithms with More Granular Differential Privacy Guarantees.
Proceedings of the 14th Innovations in Theoretical Computer Science Conference, 2023
Why Is Public Pretraining Necessary for Private Model Training?
Proceedings of the International Conference on Machine Learning, 2023
2022
Discrete Gaussian for Differential Privacy.
J. Priv. Confidentiality, 2022
Composition of Differential Privacy & Privacy Amplification by Subsampling.
CoRR, 2022
Debugging Differential Privacy: A Case Study for Privacy Auditing.
CoRR, 2022
Public Data-Assisted Mirror Descent for Private Model Training.
Proceedings of the International Conference on Machine Learning, 2022
Hyperparameter Tuning with Renyi Differential Privacy.
Proceedings of the Tenth International Conference on Learning Representations, 2022
A Private and Computationally-Efficient Estimator for Unbounded Gaussians.
Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022
2021
Private Hypothesis Selection.
IEEE Trans. Inf. Theory, 2021
Algorithmic Stability for Adaptive Data Analysis.
SIAM J. Comput., 2021
The Permute-and-Flip Mechanism is Identical to Report-Noisy-Max with Exponential Noise.
CoRR, 2021
Privately Learning Subspaces.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021
Leveraging Public Data for Practical Private Query Release.
Proceedings of the 38th International Conference on Machine Learning, 2021
The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation.
Proceedings of the 38th International Conference on Machine Learning, 2021
PAC-Bayes, MAC-Bayes and Conditional Mutual Information: Fast rate bounds that handle general VC classes.
Proceedings of the Conference on Learning Theory, 2021
Evading the Curse of Dimensionality in Unconstrained Private GLMs.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021
2020
Multi-Central Differential Privacy.
CoRR, 2020
New Oracle-Efficient Algorithms for Private Synthetic Data Release.
Proceedings of the 37th International Conference on Machine Learning, 2020
Open Problem: Information Complexity of VC Learning.
Proceedings of the Conference on Learning Theory, 2020
Reasoning About Generalization via Conditional Mutual Information.
Proceedings of the Conference on Learning Theory, 2020
2019
Make Up Your Mind: The Price of Online Queries in Differential Privacy.
J. Priv. Confidentiality, 2019
A Hybrid Approach to Privacy-Preserving Federated Learning - (Extended Abstract).
Inform. Spektrum, 2019
Towards Instance-Optimal Private Query Release.
Proceedings of the Thirtieth Annual ACM-SIAM Symposium on Discrete Algorithms, 2019
Average-Case Averages: Private Algorithms for Smooth Sensitivity and Mean Estimation.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019
A Hybrid Approach to Privacy-Preserving Federated Learning.
Proceedings of the 12th ACM Workshop on Artificial Intelligence and Security, 2019
2018
A Hybrid Approach to Privacy-Preserving Federated Learning.
CoRR, 2018
Composable and versatile privacy via truncated CDP.
Proceedings of the 50th Annual ACM SIGACT Symposium on Theory of Computing, 2018
The Limits of Post-Selection Generalization.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018
Calibrating Noise to Variance in Adaptive Data Analysis.
Proceedings of the Conference On Learning Theory, 2018
2017
Pseudorandomness and Fourier-Growth Bounds for Width-3 Branching Programs.
Theory Comput., 2017
Subgaussian Tail Bounds via Stability Arguments.
CoRR, 2017
Tight Lower Bounds for Differentially Private Selection.
Proceedings of the 58th IEEE Annual Symposium on Foundations of Computer Science, 2017
Generalization for Adaptively-chosen Estimators via Stable Median.
Proceedings of the 30th Conference on Learning Theory, 2017
2016
Between Pure and Approximate Differential Privacy.
J. Priv. Confidentiality, 2016
Concentrated Differential Privacy: Simplifications, Extensions, and Lower Bounds.
IACR Cryptol. ePrint Arch., 2016
2015
Pseudorandomness for Read-Once, Constant-Depth Circuits.
CoRR, 2015
Robust Traceability from Trace Amounts.
Proceedings of the IEEE 56th Annual Symposium on Foundations of Computer Science, 2015
Interactive Fingerprinting Codes and the Hardness of Preventing False Discovery.
Proceedings of The 28th Conference on Learning Theory, 2015
2014
Pseudorandomness and Fourier Growth Bounds for Width 3 Branching Programs.
Electron. Colloquium Comput. Complex., 2014
Weighted Polynomial Approximations: Limits for Learning and Pseudorandomness.
Electron. Colloquium Comput. Complex., 2014
2013
Pseudorandomness for Regular Branching Programs via Fourier Analysis.
Electron. Colloquium Comput. Complex., 2013
2012
Pseudorandomness for Permutation Branching Programs Without the Group Theory.
Electron. Colloquium Comput. Complex., 2012
Hierarchical Heavy Hitters with the Space Saving Algorithm.
Proceedings of the 14th Meeting on Algorithm Engineering & Experiments, 2012
2011
Learning Hurdles for Sleeping Experts.
Electron. Colloquium Comput. Complex., 2011
2010
A Rigorous Extension of the Schönhage-Strassen Integer Multiplication Algorithm Using Complex Interval Arithmetic
Proceedings of the Proceedings Seventh International Conference on Computability and Complexity in Analysis, 2010