← 研踪 PaperTrailarXiv:2202.08312 · v3
Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams
首次提交 2022-02-17 03:39
版本更新 2023-01-18 08:08
雷达观测 2026-10-29 15:15
摘要
Motivated by recent applications requiring differential privacy over adaptive streams, we investigate the question of optimal instantiations of the matrix mechanism in this setting. We prove fundamental theoretical results on the applicability of matrix factorizations to adaptive streams, and provide a parameter-free fixed-point algorithm for computing optimal factorizations. We instantiate this framework with respect to concrete matrices which arise naturally in machine learning, and train user-level differentially private models with the resulting optimal mechanisms, yielding significant improvements in a notable problem in federated learning with user-level differential privacy.
作者备注：33 pages, 6 figures. Associated code at https://github.com/google-research/federated/tree/master/dp_matrix_factorization
论文发现出处
这些页面提供论文线索，不代表同行评审或质量认证。
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v3 · 2023-01-18 08:08 · 最新观测版本
Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams
Motivated by recent applications requiring differential privacy over adaptive streams, we investigate the question of optimal instantiations of the matrix mechanism in this setting. We prove fundamental theoretical results on the applicability of matrix factorizations to adaptive streams, and provide a parameter-free fixed-point algorithm for computing optimal factorizations. We instantiate this framework with respect to concrete matrices which arise naturally in machine learning, and train user-level differentially private models with the resulting optimal mechanisms, yielding significant improvements in a notable problem in federated learning with user-level differential privacy.
查看此版本解读 →查看此版本原文 ↗