Paper Info
Title
A novel twin minimax probability machine for classification and regression
Abstract
As an excellent machine learning tool, the minimax probability machine (MPM) has been widely used in many fields. However, MPM does not include a regularization term for the construction of the separating hyperplane, and it needs to solve a large-scale second-order cone programming problem (SOCP) in the solution process, which greatly limits it development and application. In this paper, to improve the performance of MPM, we propose a novel binary classification method called twin minimax probability machine classification (TMPMC). The TMPMC constructs two non-parallel hyperplanes for final classification by solving two smaller SOCPs to improve the performance of the MPM. For each hyperplane, TMPMC attempts to minimize the worst case (maximum) probability that a class of samples is misclassified while being as far away as possible from the other class. Additionally, we extend TMPMC to the regression problem and propose a new regularized twin minimax probability machine regression (TMPMR). Intuitively, the idea of TMPMR is to convert the regression problem into a classification problem to solve. Both TMPMC and TMPMR avoid the assumption of distribution of conditional density. Finally, we extend the linear models of TMPMC and TMPMR to nonlinear case. Experimental results on several datasets show that TMPMC and TMPMR are competitive in terms of generalization performance compared to other algorithms. (C) 2020 Elsevier B.V. All rights reserved.
Year
DOI
Venue
2020
10.1016/j.knosys.2020.105703
Knowledge-Based Systems
Keywords
DocType
Volume
Minimax probability machine,Classification,Regression,Non-parallel hyperplane,Second-order cone programming
Journal
196
ISSN
Citations 
PageRank 
0950-7051
0
0.34
References 
Authors
0
2
Name
Order
Citations
PageRank
Jun Ma14719.80
Jumei Shen200.68