Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners

Authors: Rachel Redberg, Antti Koskela, Yu-Xiang Wang
Published: 2023-12-31

Source: https://arxiv.org/abs/2401.00583

PDF: https://arxiv.org/pdf/2401.00583

AIにより推定されたラベル

プライバシー保護手法 透かし評価 ハイパーパラメータ調整

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

In the arena of privacy-preserving machine learning, differentially private stochastic gradient descent (DP-SGD) has outstripped the objective perturbation mechanism in popularity and interest. Though unrivaled in versatility, DP-SGD requires a non-trivial privacy overhead (for privately tuning the model’s hyperparameters) and a computational complexity which might be extravagant for simple models such as linear and logistic regression. This paper revamps the objective perturbation mechanism with tighter privacy analyses and new computational tools that boost it to perform competitively with DP-SGD on unconstrained convex generalized linear problems.