Large margin multiclass Gaussian classification with differential privacy

DOI10.1007/978-3-642-19896-0_9MaRDI QIDQ3003503zbMATH OpenOpenAlexFDO

Authors Manas A. Pathak, B. Raj

Publication date 27 May 2011

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1005.0063

Mathematics Subject Classification ID

Data encryption (aspects in computer science) (68P25) Learning and adaptive systems in artificial intelligence (68T05)

Abstract: As increasing amounts of sensitive personal information is aggregated into data repositories, it has become important to develop mechanisms for processing the data without revealing information about individual data instances. The differential privacy model provides a framework for the development and theoretical analysis of such mechanisms. In this paper, we propose an algorithm for learning a discriminatively trained multi-class Gaussian classifier that satisfies differential privacy using a large margin loss function with a perturbed regularization term. We present a theoretical upper bound on the excess risk of the classifier introduced by the perturbation.

Recommendations

• Differentially private empirical risk minimization
• Differentially private nearest neighbor classification
• Differentially private naive Bayes learning over multiple data sources
• Differential Privacy: A Survey of Results
• The algorithmic foundations of differential privacy

Cites work

• Advances in Cryptology – CRYPTO 2004
• Differential Privacy
• Differentially private empirical risk minimization
• Finite mixture models
• scientific article; zbMATH DE number 3023295 (Why is no real title available?)
• Semidefinite Programming
• Theory of Cryptography
• Training a Support Vector Machine in the Primal
• What can we learn privately?

Cited in

(4)

• Differentially private nearest neighbor classification
• Differentially private naive Bayes learning over multiple data sources
• An Interpretable Graph-Based Mapping of Trustworthy Machine Learning Research
• Differentially private empirical risk minimization

Describes a project that uses

Uses Software

• CVX
• PrivateLR
• SuLQ

This page was built for publication: Large margin multiclass Gaussian classification with differential privacy

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3003503)