paper-with-me

홈 › Papers

Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach

2023-11-24 · Xinwei Zhang, Zhiqi Bu, Zhiwei Steven Wu, Mingyi Hong

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, using DPSGD-GC to ensure Differential Privacy (DP) comes at the cost of model performance degradation due to DP noise injection and gradient clipping. Existing research has extensively analyzed the theoretical convergence of DPSGD-GC, and has shown that it only converges when using large clipping thresholds that are dependent on problem-specific parameters. Unfortunately, these parameters are often unknown in practice, making it hard to choose the optimal clipping threshold. Therefore, in practice, 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 not only offers a diminishing utility bound without inducing a constant clipping bias, but 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. Additionally, we demonstrate that under mild conditions, our algorithm can achieve nearly the same utility bound as DPSGD without gradient clipping. Our empirical results on Cifar-10/100 and E2E datasets, show that the proposed algorithm achieves higher accuracies than DPSGD while maintaining the same level of DP guarantee.

📄 PDF Abstract BibTeX arXiv:2311.14632

Code (1)

564612540/DiceSGD 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Gradient Clipping One difficulty that arises with optimization of deep neural networks is that large parameter gradients can lead an SGD optimizer to update…

Similar Papers 제목 키워드 기반

DP-Muon: Differentially Private Optimization via Matrix-Orthogonalized Momentum

2026-05-13 · Jihwan Kim, Chenglin Fan arxiv

We study differentially private (DP) training with Muon, a matrix-valued optimizer that updates hidden-layer weights using momentum followed by Newton--Schulz orthogonalization. While DP-SGD is well understood, the inter…

DC-SGD: Differentially Private SGD with Dynamic Clipping through Gradient Norm Distribution Estimation

2025-03-29 · Chengkun Wei, Weixian Li, Chen Gong, Wenzhi Chen

Differentially Private Stochastic Gradient Descent (DP-SGD) is a widely adopted technique for privacy-preserving deep learning. A critical challenge in DP-SGD is selecting the optimal clipping threshold C, which involves…

Deep Learningimage-classificationImage ClassificationPrivacy Preserving+1

DP-MacAdam: Differentially Private Mechanism with Adaptive Clipping and Adaptive Momentum

2026-06-03 · Naima Tasnim, Lalitha Sankar, Oliver Kosut arxiv

Differentially private stochastic gradient descent (DP-SGD) has become the standard framework for privacy-preserving machine learning, yet its reliance on a fixed gradient clipping threshold to limit sensitivity remains …

On the Convergence of Differentially Private Federated Learning on Non-Lipschitz Objectives, and with Normalized Client Updates

2021-06-13 · Rudrajit Das, Abolfazl Hashemi, Sujay Sanghavi, Inderjit S. Dhillon

There is a dearth of convergence results for differentially private federated learning (FL) with non-Lipschitz objective functions (i.e., when gradient norms are not bounded). The primary reason for this is that the clip…

BenchmarkingFederated LearningQuantizationSensitivity

Dyn-D$^2$P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee

2025-05-10 · Zehan Zhu, Yan Huang, Xin Wang, Shouling Ji 외

Most existing decentralized learning methods with differential privacy (DP) guarantee rely on constant gradient clipping bounds and fixed-level DP Gaussian noises for each node throughout the training process, leading to…