A new constrained maximum margin approach to discriminative learning of Bayesian classifiers

• Published in: Frontiers of information technology & electronic engineering Vol. 19; no. 5; pp. 639 - 650
• Main Authors: Guo, Ke, Liu, Xia-bi, Guo, Lun-hao, Li, Zong-jie, Geng, Zeng-min
• Format: Journal Article
• Language: English
• Published: Hangzhou Zhejiang University Press 01.05.2018; Springer Nature B.V
• Subjects: Algorithms; Bayesian analysis; Classification; Classifiers; Communications Engineering; Computer Hardware; Computer Science; Computer Systems Organization and Communication Networks; Constraints; Datasets; Electrical Engineering; Electronics and Microelectronics; Information technology; Instrumentation; Machine learning; Networks; Nonlinear programming; Optimization; Pattern classification; Probabilistic models; Probability; Probability distribution; Support vector machines; Gaussian mixture models; Statistical modeling; TP391; Discriminative learning; UCI datasets; Bayesian pattern classifiers
• ISSN: 2095-9184; 2095-9230
• DOI: 10.1631/FITEE.1700007

We propose a novel discriminative learning approach for Bayesian pattern classification, called ‘constrained maximum margin (CMM)’. We define the margin between two classes as the difference between the minimum decision value for positive samples and the maximum decision value for negative samples. The learning problem is to maximize the margin under the constraint that each training pattern is classified correctly. This nonlinear programming problem is solved using the sequential unconstrained minimization technique. We applied the proposed CMM approach to learn Bayesian classifiers based on Gaussian mixture models, and conducted the experiments on 10 UCI datasets. The performance of our approach was compared with those of the expectation-maximization algorithm, the support vector machine, and other state-of-the-art approaches. The experimental results demonstrated the effectiveness of our approach.