Differentially Private Learning with Per-Sample Adaptive Clipping

TL;DR

This paper introduces DP-PSAC, a novel differentially private learning algorithm with adaptive per-sample clipping that reduces hyperparameter tuning and improves convergence and performance across vision and language tasks.

Contribution

The paper proposes a non-monotonic adaptive clipping method for differential privacy that reduces deviation and hyperparameter tuning compared to existing normalization-based approaches.

Findings

DP-PSAC achieves lower non-vanishing bounds than NSGD/Auto-S.

Experimental results show DP-PSAC outperforms or matches state-of-the-art methods.

Theoretical analysis confirms convergence guarantees of DP-PSAC.

Abstract

Privacy in AI remains a topic that draws attention from researchers and the general public in recent years. As one way to implement privacy-preserving AI, differentially private learning is a framework that enables AI models to use differential privacy (DP). To achieve DP in the learning process, existing algorithms typically limit the magnitude of gradients with a constant clipping, which requires carefully tuned due to its significant impact on model performance. As a solution to this issue, latest works NSGD and Auto-S innovatively propose to use normalization instead of clipping to avoid hyperparameter tuning. However, normalization-based approaches like NSGD and Auto-S rely on a monotonic weight function, which imposes excessive weight on small gradient samples and introduces extra deviation to the update. In this paper, we propose a Differentially Private Per-Sample Adaptive Clipping (DP-PSAC) algorithm based on a non-monotonic adaptive weight function, which guarantees privacy without the typical hyperparameter tuning process of using a constant clipping while significantly reducing the deviation between the update and true batch-averaged gradient. We provide a rigorous theoretical convergence analysis and show that with convergence rate at the same order, the proposed algorithm achieves a lower non-vanishing bound, which is maintained over training iterations, compared with NSGD/Auto-S. In addition, through extensive experimental evaluation, we show that DP-PSAC outperforms or matches the state-of-the-art methods on multiple main-stream vision and language tasks.