TY - JOUR
T1 - K-Times Markov Sampling for SVMC
AU - Zou, Bin
AU - Xu, Chen
AU - Lu, Yang
AU - Tang, Yuan Yan
AU - Xu, Jie
AU - You, Xinge
N1 - This work was supported in part by NSFC Project under Grant 61403132, Grant 61370002, and Grant 61272203, in part by Hubei Key Laboratory of Applied Mathematics, Hubei University, Hubei Province Technologies RD Program under Grant XYJ2014000459, in part by the Natural Sciences and Engineering Research Council of Canada under Grant RGPIN-2016-05024, in part by the Shenzhen Research Council under Grant CXZZ20150814155434903 and Grant JCYJ20140819154343378, and in part by NFS of Hubei Provience under Grant 2015CFB404.
Publisher Copyright:
© 2017 IEEE.
PY - 2018/4
Y1 - 2018/4
N2 - Support vector machine (SVM) is one of the most widely used learning algorithms for classification problems. Although SVM has good performance in practical applications, it has high algorithmic complexity as the size of training samples is large. In this paper, we introduce SVM classification (SVMC) algorithm based on k-times Markov sampling and present the numerical studies on the learning performance of SVMC with k-times Markov sampling for benchmark data sets. The experimental results show that the SVMC algorithm with k-times Markov sampling not only have smaller misclassification rates, less time of sampling and training, but also the obtained classifier is more sparse compared with the classical SVMC and the previously known SVMC algorithm based on Markov sampling. We also give some discussions on the performance of SVMC with k-times Markov sampling for the case of unbalanced training samples and large-scale training samples.
AB - Support vector machine (SVM) is one of the most widely used learning algorithms for classification problems. Although SVM has good performance in practical applications, it has high algorithmic complexity as the size of training samples is large. In this paper, we introduce SVM classification (SVMC) algorithm based on k-times Markov sampling and present the numerical studies on the learning performance of SVMC with k-times Markov sampling for benchmark data sets. The experimental results show that the SVMC algorithm with k-times Markov sampling not only have smaller misclassification rates, less time of sampling and training, but also the obtained classifier is more sparse compared with the classical SVMC and the previously known SVMC algorithm based on Markov sampling. We also give some discussions on the performance of SVMC with k-times Markov sampling for the case of unbalanced training samples and large-scale training samples.
KW - K-times Markov sampling
KW - learning performance
KW - support vector machine classification (SVMC)
KW - uniform ergodic Markov chain (u.e.M.c.)
UR - http://www.scopus.com/inward/record.url?scp=85028931500&partnerID=8YFLogxK
U2 - 10.1109/TNNLS.2016.2609441
DO - 10.1109/TNNLS.2016.2609441
M3 - Journal article
C2 - 28749357
AN - SCOPUS:85028931500
SN - 2162-237X
VL - 29
SP - 1328
EP - 1341
JO - IEEE Transactions on Neural Networks and Learning Systems
JF - IEEE Transactions on Neural Networks and Learning Systems
IS - 4
ER -
