A Hierarchical Convex Optimization for Multiclass SVM Achieving Maximum Pairwise Margins with Least Empirical Hinge-Loss
Optimization and Control
2020-04-20 v1 Signal Processing
Abstract
In this paper, we formulate newly a hierarchical convex optimization for multiclass SVM achieving maximum pairwise margins with least empirical hinge-loss. This optimization problem is a most faithful as well as robust multiclass extension of an NP-hard hierarchical optimization appeared for the first time in the seminal paper by C.~Cortes and V.~Vapnik almost 25 years ago. By extending the very recent fixed point theoretic idea [Yamada-Yamagishi 2019] with the generalized hinge loss function [Crammer-Singer 2001], we show that the hybrid steepest descent method [Yamada 2001] in the computational fixed point theory is applicable to this much more complex hierarchical convex optimization problem.
Keywords
Cite
@article{arxiv.2004.08180,
title = {A Hierarchical Convex Optimization for Multiclass SVM Achieving Maximum Pairwise Margins with Least Empirical Hinge-Loss},
author = {Yunosuke Nakayama and Masao Yamagishi and Isao Yamada},
journal= {arXiv preprint arXiv:2004.08180},
year = {2020}
}