Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement

• URL: http://arxiv.org/abs/2408.10456v1
• Date: Mon, 19 Aug 2024 23:57:31 GMT
• Title: Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement
• Authors: Jeremiah Birrell, Reza Ebrahimi, Rouzbeh Behnia, Jason Pacheco,
• Abstract summary: DP-SGD gradients in a fixed-size subsampling regime exhibit lower variance in practice in addition to memory usage benefits. We show for the first time that the widely-used Poisson subsampling and FSwoR with replace-one adjacency have the same privacy to leading order in the sampling probability.
• Score: 6.494759487261151
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Differentially private stochastic gradient descent (DP-SGD) has been instrumental in privately training deep learning models by providing a framework to control and track the privacy loss incurred during training. At the core of this computation lies a subsampling method that uses a privacy amplification lemma to enhance the privacy guarantees provided by the additive noise. Fixed size subsampling is appealing for its constant memory usage, unlike the variable sized minibatches in Poisson subsampling. It is also of interest in addressing class imbalance and federated learning. However, the current computable guarantees for fixed-size subsampling are not tight and do not consider both add/remove and replace-one adjacency relationships. We present a new and holistic R{\'e}nyi differential privacy (RDP) accountant for DP-SGD with fixed-size subsampling without replacement (FSwoR) and with replacement (FSwR). For FSwoR we consider both add/remove and replace-one adjacency. Our FSwoR results improves on the best current computable bound by a factor of $4$. We also show for the first time that the widely-used Poisson subsampling and FSwoR with replace-one adjacency have the same privacy to leading order in the sampling probability. Accordingly, our work suggests that FSwoR is often preferable to Poisson subsampling due to constant memory usage. Our FSwR accountant includes explicit non-asymptotic upper and lower bounds and, to the authors' knowledge, is the first such analysis of fixed-size RDP with replacement for DP-SGD. We analytically and empirically compare fixed size and Poisson subsampling, and show that DP-SGD gradients in a fixed-size subsampling regime exhibit lower variance in practice in addition to memory usage benefits.

Related papers

• To Shuffle or not to Shuffle: Auditing DP-SGD with Shuffling [25.669347036509134]
  We analyze Differentially Private Gradient Descent (DP-SGD) with shuffling. We show that state-of-the-art DP models trained with shuffling appreciably overestimated privacy guarantees (up to 4x) Our work empirically attests to the risk of using shuffling instead of Poisson sub-sampling vis-a-vis the actual privacy leakage of DP-SGD.
  arXiv  Detail & Related papers  (2024-11-15T22:34:28Z)
• Scalable DP-SGD: Shuffling vs. Poisson Subsampling [61.19794019914523]
  We provide new lower bounds on the privacy guarantee of the multi-epoch Adaptive Linear Queries (ABLQ) mechanism with shuffled batch sampling. We show substantial gaps when compared to Poisson subsampling; prior analysis was limited to a single epoch. We introduce a practical approach to implement Poisson subsampling at scale using massively parallel computation.
  arXiv  Detail & Related papers  (2024-11-06T19:06:16Z)
• Noise Variance Optimization in Differential Privacy: A Game-Theoretic Approach Through Per-Instance Differential Privacy [7.264378254137811]
  Differential privacy (DP) can measure privacy loss by observing the changes in the distribution caused by the inclusion of individuals in the target dataset. DP has been prominent in safeguarding datasets in machine learning in industry giants like Apple and Google. We propose per-instance DP (pDP) as a constraint, measuring privacy loss for each data instance and optimizing noise tailored to individual instances.
  arXiv  Detail & Related papers  (2024-04-24T06:51:16Z)
• How Private are DP-SGD Implementations? [61.19794019914523]
  We show that there can be a substantial gap between the privacy analysis when using the two types of batch sampling. Our result shows that there can be a substantial gap between the privacy analysis when using the two types of batch sampling.
  arXiv  Detail & Related papers  (2024-03-26T13:02:43Z)
• Make Landscape Flatter in Differentially Private Federated Learning [69.78485792860333]
  We propose a novel DPFL algorithm named DP-FedSAM, which leverages gradient perturbation to mitigate the negative impact of DP. Specifically, DP-FedSAM integrates local flatness models with better stability and weight robustness, which results in the small norm of local updates and robustness to DP noise. Our algorithm achieves state-of-the-art (SOTA) performance compared with existing SOTA baselines in DPFL.
  arXiv  Detail & Related papers  (2023-03-20T16:27:36Z)
• Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimization [94.06564567766475]
  DP-SGD and DP-NSGD mitigate the risk of large models memorizing sensitive training data. We show that these two algorithms achieve similar best accuracy while DP-NSGD is comparatively easier to tune than DP-SGD.
  arXiv  Detail & Related papers  (2022-06-27T03:45:02Z)
• Auditing Differential Privacy in High Dimensions with the Kernel Quantum R\'enyi Divergence [29.796646032324514]
  We propose relaxations of differential privacy based on new divergences on probability distributions. We show that the regularized kernel R'enyi divergence can be estimated from samples even in high dimensions.
  arXiv  Detail & Related papers  (2022-05-27T12:34:17Z)
• On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times [51.61278695776151]
  Federated Learning (FL) is well known for its privacy protection when training machine learning models among distributed clients collaboratively. Recent studies have pointed out that the naive FL is susceptible to gradient leakage attacks. Differential Privacy (DP) emerges as a promising countermeasure to defend against gradient leakage attacks.
  arXiv  Detail & Related papers  (2021-01-11T19:43:12Z)
• Privacy Amplification via Random Check-Ins [38.72327434015975]
  Differentially Private Gradient Descent (DP-SGD) forms a fundamental building block in many applications for learning over sensitive data. In this paper, we focus on conducting iterative methods like DP-SGD in the setting of federated learning (FL) wherein the data is distributed among many devices (clients) Our main contribution is the emphrandom check-in distributed protocol, which crucially relies only on randomized participation decisions made locally and independently by each client.
  arXiv  Detail & Related papers  (2020-07-13T18:14:09Z)
• Differentially Private Federated Learning with Laplacian Smoothing [72.85272874099644]
  Federated learning aims to protect data privacy by collaboratively learning a model without sharing private data among users. An adversary may still be able to infer the private training data by attacking the released model. Differential privacy provides a statistical protection against such attacks at the price of significantly degrading the accuracy or utility of the trained models.
  arXiv  Detail & Related papers  (2020-05-01T04:28:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.