Support vector machines and linear regression coincide with very high-dimensional features

Author name not available (Why is that?)

Publication date: 28 May 2021

Abstract: The support vector machine (SVM) and minimum Euclidean norm least squares regression are two fundamentally different approaches to fitting linear models, but they have recently been connected in models for very high-dimensional data through a phenomenon of support vector proliferation, where every training example used to fit an SVM becomes a support vector. In this paper, we explore the generality of this phenomenon and make the following contributions. First, we prove a super-linear lower bound on the dimension (in terms of sample size) required for support vector proliferation in independent feature models, matching the upper bounds from previous works. We further identify a sharp phase transition in Gaussian feature models, bound the width of this transition, and give experimental support for its universality. Finally, we hypothesize that this phase transition occurs only in much higher-dimensional settings in the

e l l_{1}

variant of the SVM, and we present a new geometric characterization of the problem that may elucidate this phenomenon for the general

e l l_{p}

case.

Has companion code repository: https://github.com/scO0rpion/SVM-Proliferation-NIPS2021

This page was built for publication: Support vector machines and linear regression coincide with very high-dimensional features

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6368842)