Rajkumar, Arun and Agarwal, Shivani (2012) Differentially private stochastic gradient descent algorithm for multiparty classification. In: Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics (AISTATS-12), Apr 21, 2012, La Palma, Canary Islands.
PDF
Art_Intel_Sta_933_2012.pdf - Published Version Restricted to Registered users only Download (346kB) | Request a copy |
Abstract
We consider the problem of developing privacy-preserving machine learning algorithms in a dis-tributed multiparty setting. Here different parties own different parts of a data set, and the goal is to learn a classifier from the entire data set with-out any party revealing any information about the individual data points it owns. Pathak et al [7]recently proposed a solution to this problem in which each party learns a local classifier from its own data, and a third party then aggregates these classifiers in a privacy-preserving manner using a cryptographic scheme. The generaliza-tion performance of their algorithm is sensitive to the number of parties and the relative frac-tions of data owned by the different parties. In this paper, we describe a new differentially pri-vate algorithm for the multiparty setting that uses a stochastic gradient descent based procedure to directly optimize the overall multiparty ob-jective rather than combining classifiers learned from optimizing local objectives. The algorithm achieves a slightly weaker form of differential privacy than that of [7], but provides improved generalization guarantees that do not depend on the number of parties or the relative sizes of the individual data sets. Experimental results corrob-orate our theoretical findings.
Item Type: | Conference Paper |
---|---|
Publisher: | JMLR |
Additional Information: | Copyright of this article belongs to JMLR. |
Department/Centre: | Division of Electrical Sciences > Computer Science & Automation |
Date Deposited: | 19 Nov 2013 06:35 |
Last Modified: | 19 Nov 2013 06:35 |
URI: | http://eprints.iisc.ac.in/id/eprint/47772 |
Actions (login required)
View Item |