Fast John Ellipsoid Computation with Differential Privacy Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Xiaoyu, Liang, Yingyu, Shi, Zhenmei, Song, Zhao, Yu, Junwei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916623530590208
author Li, Xiaoyu
Liang, Yingyu
Shi, Zhenmei
Song, Zhao
Yu, Junwei
author_facet Li, Xiaoyu
Liang, Yingyu
Shi, Zhenmei
Song, Zhao
Yu, Junwei
contents Determining the John ellipsoid - the largest volume ellipsoid contained within a convex polytope - is a fundamental problem with applications in machine learning, optimization, and data analytics. Recent work has developed fast algorithms for approximating the John ellipsoid using sketching and leverage score sampling techniques. However, these algorithms do not provide privacy guarantees for sensitive input data. In this paper, we present the first differentially private algorithm for fast John ellipsoid computation. Our method integrates noise perturbation with sketching and leverages score sampling to achieve both efficiency and privacy. We prove that (1) our algorithm provides $(ε,δ)$-differential privacy and the privacy guarantee holds for neighboring datasets that are $ε_0$-close, allowing flexibility in the privacy definition; (2) our algorithm still converges to a $(1+ξ)$-approximation of the optimal John ellipsoid in $Θ(ξ^{-2}(\log(n/δ_0) + (Lε_0)^{-2}))$ iterations where $n$ is the number of data point, $L$ is the Lipschitz constant, $δ_0$ is the failure probability, and $ε_0$ is the closeness of neighboring input datasets. Our theoretical analysis demonstrates the algorithm's convergence and privacy properties, providing a robust approach for balancing utility and privacy in John ellipsoid computation. This is the first differentially private algorithm for fast John ellipsoid computation, opening avenues for future research in privacy-preserving optimization techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2408_06395
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Fast John Ellipsoid Computation with Differential Privacy Optimization
Li, Xiaoyu
Liang, Yingyu
Shi, Zhenmei
Song, Zhao
Yu, Junwei
Data Structures and Algorithms
Cryptography and Security
Machine Learning
Determining the John ellipsoid - the largest volume ellipsoid contained within a convex polytope - is a fundamental problem with applications in machine learning, optimization, and data analytics. Recent work has developed fast algorithms for approximating the John ellipsoid using sketching and leverage score sampling techniques. However, these algorithms do not provide privacy guarantees for sensitive input data. In this paper, we present the first differentially private algorithm for fast John ellipsoid computation. Our method integrates noise perturbation with sketching and leverages score sampling to achieve both efficiency and privacy. We prove that (1) our algorithm provides $(ε,δ)$-differential privacy and the privacy guarantee holds for neighboring datasets that are $ε_0$-close, allowing flexibility in the privacy definition; (2) our algorithm still converges to a $(1+ξ)$-approximation of the optimal John ellipsoid in $Θ(ξ^{-2}(\log(n/δ_0) + (Lε_0)^{-2}))$ iterations where $n$ is the number of data point, $L$ is the Lipschitz constant, $δ_0$ is the failure probability, and $ε_0$ is the closeness of neighboring input datasets. Our theoretical analysis demonstrates the algorithm's convergence and privacy properties, providing a robust approach for balancing utility and privacy in John ellipsoid computation. This is the first differentially private algorithm for fast John ellipsoid computation, opening avenues for future research in privacy-preserving optimization techniques.
title Fast John Ellipsoid Computation with Differential Privacy Optimization
topic Data Structures and Algorithms
Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2408.06395