Phase transition in the hard-margin support vector machines

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Scopus citations

Abstract

This paper establishes a phase transition for convergence of the hard-margin support vector machines (SVM) in high dimensional and numerous data regime, drawn from a Gaussian mixture distribution. Particularly, we characterize the maximum number of training samples that the hard-margin SVM is capable of perfectly separating. Under the assumption that the number of training samples is less than this threshold, we provide a sharp characterization of the margin parameter and the classification error performance of the hard-margin SVM classifier. Our analysis, validated through a set of numerical experiments, is based on the convex Gaussian min-max framework.
Original languageEnglish (US)
Title of host publication2019 IEEE 8th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP)
PublisherIEEE
Pages415-419
Number of pages5
ISBN (Print)9781728155494
DOIs
StatePublished - Mar 6 2020

Bibliographical note

KAUST Repository Item: Exported on 2020-10-01

Fingerprint

Dive into the research topics of 'Phase transition in the hard-margin support vector machines'. Together they form a unique fingerprint.

Cite this