资源论文Differentially Private Chi-squared Test by Unit Circle Mechanism

Differentially Private Chi-squared Test by Unit Circle Mechanism

2020-03-09 | |  65 |   50 |   0

Abstract

This paper develops differentially private mechanisms for 图片.png test of independence. While existing works put their effort into properly controlling the type-I error, in addition to that, we investigate the type-II error of differentially priva mechanisms. Based on the analysis, we present unit circle mechanism: a novel differentially private mechanism based on the geometrical property of the test statistics. Compared to existing output perturbation mechanisms, our mechanism improves the dominated term of the type-II error from O(1) to 图片.png where N is the sample size. Furthermore, we introduce novel procedures for multiple 图片.png tests by incorporating the unit circle mechanism into the sparse vector technique and the exponential mechanism. These procedures can control the family-wise error rate (FWER) properly, which has never been attained by existing mechanisms.

上一篇:Variational Inference for Sparse and Undirected Models

下一篇:Failures of Gradient-Based Deep Learning

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...