Saved in:
Bibliographic Details
Main Authors: Dette, Holger, Graw, Carina
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.12553
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929351207944192
author Dette, Holger
Graw, Carina
author_facet Dette, Holger
Graw, Carina
contents Stochastic Gradient Descent (SGD) is a widely used tool in machine learning. In the context of Differential Privacy (DP), SGD has been well studied in the last years in which the focus is mainly on convergence rates and privacy guarantees. While in the non private case, uncertainty quantification (UQ) for SGD by bootstrap has been addressed by several authors, these procedures cannot be transferred to differential privacy due to multiple queries to the private data. In this paper, we propose a novel block bootstrap for SGD under local differential privacy that is computationally tractable and does not require an adjustment of the privacy budget. The method can be easily implemented and is applicable to a broad class of estimation problems. We prove the validity of our approach and illustrate its finite sample properties by means of a simulation study. As a by-product, the new method also provides a simple alternative numerical tool for UQ for non-private SGD.
format Preprint
id arxiv_https___arxiv_org_abs_2405_12553
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Uncertainty quantification by block bootstrap for differentially private stochastic gradient descent
Dette, Holger
Graw, Carina
Machine Learning
Cryptography and Security
Statistics Theory
Computation
Stochastic Gradient Descent (SGD) is a widely used tool in machine learning. In the context of Differential Privacy (DP), SGD has been well studied in the last years in which the focus is mainly on convergence rates and privacy guarantees. While in the non private case, uncertainty quantification (UQ) for SGD by bootstrap has been addressed by several authors, these procedures cannot be transferred to differential privacy due to multiple queries to the private data. In this paper, we propose a novel block bootstrap for SGD under local differential privacy that is computationally tractable and does not require an adjustment of the privacy budget. The method can be easily implemented and is applicable to a broad class of estimation problems. We prove the validity of our approach and illustrate its finite sample properties by means of a simulation study. As a by-product, the new method also provides a simple alternative numerical tool for UQ for non-private SGD.
title Uncertainty quantification by block bootstrap for differentially private stochastic gradient descent
topic Machine Learning
Cryptography and Security
Statistics Theory
Computation
url https://arxiv.org/abs/2405.12553