Arun Ganesh

Brendan McMahan

CoRR, July, 2025

Correlated Noise Mechanisms for Differentially Private Learning.

[BibT_eX]

[DOI]

Krishna Pillutla

Jalaj Upadhyay

Krishnamurthy Dvijotham

CoRR, June, 2025

Hush! Protecting Secrets During Model Training: An Indistinguishability Approach.

[BibT_eX]

[DOI]

CoRR, June, 2025

It's My Data Too: Private ML for Datasets with Multi-User Training Examples.

[BibT_eX]

[DOI]

CoRR, March, 2025

Recycling Scraps: Improving Private Learning by Leveraging Checkpoints]{Recycling Scraps: Improving Private Learning by Leveraging Checkpoints.

[BibT_eX]

[DOI]

Proc. Priv. Enhancing Technol., 2025

Learning with User-Level Differential Privacy Under Fixed Compute Budgets.

[BibT_eX]

[DOI]

Proceedings of the IEEE Conference on Secure and Trustworthy Machine Learning, 2025

The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD.

[BibT_eX]

[DOI]

Milad Nasr

Borja Balle

Matthew Jagielski

Jamie Hayes

Adam Smith

Andreas Terzis

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Near-Exact Privacy Amplification for Matrix Mechanisms.

[BibT_eX]

[DOI]

Saminul Haque

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Near-Optimal Rates for O(1)-Smooth DP-SCO with a Single Epoch and Large Batches.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Algorithmic Learning Theory, 2025

2024

Fine-Tuning Large Language Models with User-Level Differential Privacy.

[BibT_eX]

[DOI]

CoRR, 2024

Optimal Rates for DP-SCO with a Single Epoch and Large Batches.

[BibT_eX]

[DOI]

CoRR, 2024

Tight Group-Level DP Guarantees for DP-SGD with Sampling via Mixture of Gaussians Mechanisms.

[BibT_eX]

[DOI]

CoRR, 2024

Privacy Amplification for Matrix Mechanisms.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Correlated Noise Provably Beats Independent Noise for Differentially Private Learning.

[BibT_eX]

[DOI]

Krishnamurthy Dj Dvijotham

Krishna Pillutla

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Universal Algorithms for Clustering Problems.

[BibT_eX]

[DOI]

Bruce M. Maggs

Debmalya Panigrahi

ACM Trans. Algorithms, April, 2023

Robust Algorithms for TSP and Steiner Tree.

[BibT_eX]

[DOI]

Bruce M. Maggs

Debmalya Panigrahi

ACM Trans. Algorithms, April, 2023

(Amplified) Banded Matrix Factorization: A unified approach to private training.

[BibT_eX]

[DOI]

Zheng Xu

CoRR, 2023

Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks.

[BibT_eX]

[DOI]

Daogao Liu

Sewoong Oh

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Faster Differentially Private Convex Optimization via Second-Order Methods.

[BibT_eX]

[DOI]

Mahdi Haghifam

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

(Amplified) Banded Matrix Factorization: A unified approach to private training.

[BibT_eX]

[DOI]

Zheng Xu

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Why Is Public Pretraining Necessary for Private Model Training?

[BibT_eX]

[DOI]

Lun Wang

Proceedings of the International Conference on Machine Learning, 2023

Universality of Langevin Diffusion for Private Optimization, with Applications to Sampling from Rashomon Sets.

[BibT_eX]

[DOI]

Jalaj Upadhyay

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

2022

Improved Algorithms and Upper Bounds in Differential Privacy

[BibT_eX]

[DOI]

PhD thesis, 2022

Recycling Scraps: Improving Private Learning by Leveraging Intermediate Checkpoints.

[BibT_eX]

[DOI]

CoRR, 2022

Langevin Diffusion: An Almost Universal Algorithm for Private Euclidean (Convex) Optimization.

[BibT_eX]

[DOI]

Jalaj Upadhyay

CoRR, 2022

How Compression and Approximation Affect Efficiency in String Distance Measures.

[BibT_eX]

[DOI]

Proceedings of the 2022 ACM-SIAM Symposium on Discrete Algorithms, 2022

Public Data-Assisted Mirror Descent for Private Model Training.

[BibT_eX]

[DOI]

Vinith M. Suriyakumar

Om Thakkar

Proceedings of the International Conference on Machine Learning, 2022

2021

Online Service with Delay.

[BibT_eX]

[DOI]

ACM Trans. Algorithms, 2021

Universal Algorithms for Clustering.

[BibT_eX]

[DOI]

Bruce M. Maggs

Debmalya Panigrahi

CoRR, 2021

Privately Answering Counting Queries with Generalized Gaussian Mechanisms.

[BibT_eX]

[DOI]

Jiazheng Zhao

Proceedings of the 2nd Symposium on Foundations of Responsible Computing, 2021

2020

Near-Linear Time Edit Distance for Indel Channels.

[BibT_eX]

[DOI]

Aaron Sy

Proceedings of the 20th International Workshop on Algorithms in Bioinformatics, 2020

Faster Differentially Private Samplers via Rényi Divergence Analysis of Discretized Langevin MCMC.

[BibT_eX]

[DOI]

Kunal Talwar

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2019

Optimal sequence length requirements for phylogenetic tree reconstruction with indels.

[BibT_eX]

[DOI]