An ADMM Solver for the MKL-L_0/1-SVM

2023/03/08 by Yijie Shi, Bin Zhu, Shi, Yijie +1
Computer Science · Engineering · #FOS: Computer and information sciences #Face and Expression Recognition #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and ELM #Sparse and Compressive Sensing Techniques

paper · pdf · doi:10.48550/arxiv.2303.04445

openalex publication_date 2023/03/08 · openalex created_date 2023/03/10 · openalex updated_date 2026/07/28

Abstract

We formulate the Multiple Kernel Learning (abbreviated as MKL) problem for the support vector machine with the infamous (0,1)-loss function. Some first-order optimality conditions are given and then exploited to develop a fast ADMM solver for the nonconvex and nonsmooth optimization problem. A simple numerical experiment on synthetic planar data shows that our MKL-L_0/1-SVM framework could be promising.

Related

• MKL-L_0/1-SVM
• Nonlinear Kernel Support Vector Machine with 0-1 Soft Margin Loss
• Kernel Support Vector Machine Classifiers with the ℓ₀-Norm Hinge Loss
• MKL-RT: Multiple Kernel Learning for Ratio-trace Problems via Convex Optimization
• Support Vector Machine Classifier via L_0/1 Soft-Margin Loss