collaborators

8 papers

cs.LG2025

Correlated Noise Mechanisms for Differentially Private Learning

Krishna Pillutla, Jalaj Upadhyay, Christopher A. Choquette-Choo +9

This monograph explores the design and analysis of correlated noise mechanisms for differential privacy (DP), focusing on their application to private training of AI and machine le…

cs.LG2025

A Hassle-free Algorithm for Private Learning in Practice: Don't Use Tree Aggregation, Use BLTs

H. Brendan McMahan, Zheng Xu, Yanxiang Zhang

The state-of-the-art for training on-device language models for mobile keyboard applications combines federated learning (FL) with differential privacy (DP) via the DP-Follow-the-R…

cs.CR2025

An Inversion Theorem for Buffered Linear Toeplitz (BLT) Matrices and Applications to Streaming Differential Privacy

H. Brendan McMahan, Krishna Pillutla

Buffered Linear Toeplitz (BLT) matrices are a family of parameterized lower-triangular matrices that play an important role in streaming differential privacy with correlated noise.…

cs.LG2025

Federated Learning in Practice: Reflections and Projections

Katharine Daly, Hubert Eichner, Peter Kairouz +3

Federated Learning (FL) is a machine learning technique that enables multiple entities to collaboratively learn a shared model without exchanging their local data. Over the past de…

cs.LG2024

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

Zachary Charles, Arun Ganesh, Ryan McKenna +4

We investigate practical and scalable algorithms for training large language models (LLMs) with user-level differential privacy (DP) in order to provably safeguard all the examples…

cs.DS2024

Efficient and Near-Optimal Noise Generation for Streaming Differential Privacy

Krishnamurthy Dvijotham, H. Brendan McMahan, Krishna Pillutla +2

In the task of differentially private (DP) continual counting, we receive a stream of increments and our goal is to output an approximate running total of these increments, without…