English

Smoothed Hinge Loss and $\ell^{1}$ Support Vector Machines

Optimization and Control 2018-08-23 v1 Numerical Analysis

Abstract

A new algorithm is presented for solving the soft-margin Support Vector Machine (SVM) optimization problem with an 1\ell^{1} penalty. This algorithm is designed to require a modest number of passes over the data, which is an important measure of its cost for very large data sets. The algorithm uses smoothing for the hinge-loss function, and an active set approach for the 1\ell^{1} penalty.

Keywords

Cite

@article{arxiv.1808.07100,
  title  = {Smoothed Hinge Loss and $\ell^{1}$ Support Vector Machines},
  author = {Jeffrey Hajewski and Suely Oliveira and David E. Stewart},
  journal= {arXiv preprint arXiv:1808.07100},
  year   = {2018}
}

Comments

13 pp, 1 figure

R2 v1 2026-06-23T03:40:01.884Z