Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Differential Privacy, Error-feedback, Differentially private training
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: We proposed a clipped error-feedback approach to debias the clipping biase in DPSGD and proved both convergence and privacy guarantee.
Abstract: Differentially Private Stochastic Gradient Descent with Gradient Clipping (DPSGD-GC) is a powerful tool for training deep learning models using sensitive data, providing both a solid theoretical privacy guarantee and high efficiency. However, existing research has shown that DPSGD-GC only converges when using large clipping thresholds that are dependent on problem-specific parameters that are often unknown in practice. Therefore, DPSGD-GC suffers from degraded performance due to the {\it constant} bias introduced by the clipping. In our work, we propose a new error-feedback (EF) DP algorithm as an alternative to DPSGD-GC, which offers a diminishing utility bound without inducing a constant clipping bias. More importantly, it allows for an arbitrary choice of clipping threshold that is independent of the problem. We establish an algorithm-specific DP analysis for our proposed algorithm, providing privacy guarantees based on R{\'e}nyi DP. And we demonstrate that under mild conditions, our algorithm can achieve the same utility bound as DPSGD without gradient clipping. Our empirical results on standard datasets show that the proposed algorithm achieves higher accuracies than DPSGD while maintaining the same level of DP guarantee.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
Supplementary Material: pdf
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Primary Area: societal considerations including fairness, safety, privacy
Submission Number: 3859
Loading