8 papers
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…
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…
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.…
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…
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…
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…