The generalization ability of online SVM classification based on Markov sampling

Jie Xu; Yuan Yan Tang; Bin Zou; Zongben Xu; Luoqing Li; Yang Lu

doi:10.1109/TNNLS.2014.2361026

The generalization ability of online SVM classification based on Markov sampling

Jie Xu, Yuan Yan Tang, Bin Zou^*, Zongben Xu, Luoqing Li, Yang Lu

^*Corresponding author for this work

Department of Computer Science

Research output: Contribution to journal › Journal article › peer-review

45 Citations (Scopus)

Abstract

In this paper, we consider online support vector machine (SVM) classification learning algorithms with uniformly ergodic Markov chain (u.e.M.c.) samples. We establish the bound on the misclassification error of an online SVM classification algorithm with u.e.M.c. samples based on reproducing kernel Hilbert spaces and obtain a satisfactory convergence rate. We also introduce a novel online SVM classification algorithm based on Markov sampling, and present the numerical studies on the learning ability of online SVM classification based on Markov sampling for benchmark repository. The numerical studies show that the learning performance of the online SVM classification algorithm based on Markov sampling is better than that of classical online SVM classification based on random sampling as the size of training samples is larger.

Original language	English
Pages (from-to)	628-639
Number of pages	12
Journal	IEEE Transactions on Neural Networks and Learning Systems
Volume	26
Issue number	3
DOIs	https://doi.org/10.1109/TNNLS.2014.2361026
Publication status	Published - Mar 2015

User-Defined Keywords

Generalization ability
Markov sampling
online support vector machine (SVM) classification
uniformly ergodic Markov chain (u.e.M.c.).

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/TNNLS.2014.2361026

Cite this

@article{6d40280cd75c49e18b2b4cc2f66e46c1,

title = "The generalization ability of online SVM classification based on Markov sampling",

abstract = "In this paper, we consider online support vector machine (SVM) classification learning algorithms with uniformly ergodic Markov chain (u.e.M.c.) samples. We establish the bound on the misclassification error of an online SVM classification algorithm with u.e.M.c. samples based on reproducing kernel Hilbert spaces and obtain a satisfactory convergence rate. We also introduce a novel online SVM classification algorithm based on Markov sampling, and present the numerical studies on the learning ability of online SVM classification based on Markov sampling for benchmark repository. The numerical studies show that the learning performance of the online SVM classification algorithm based on Markov sampling is better than that of classical online SVM classification based on random sampling as the size of training samples is larger.",

keywords = "Generalization ability, Markov sampling, online support vector machine (SVM) classification, uniformly ergodic Markov chain (u.e.M.c.).",

author = "Jie Xu and {Yan Tang}, Yuan and Bin Zou and Zongben Xu and Luoqing Li and Yang Lu",

note = "This work was supported in part by the National Science Foundation (NSF) of China under Project 11371007, Project 61370002, and Project 61403132, in part by the Multiyear Research, University of Macau, Macau, China, under Grant MYRG205(Y1-L4)-FST11-TYY and Grant MYRG187(Y1-L3)-FST11-TYY, in part by the Start-Up Research, University of Macau, under Grant SRG010-FST11-TYY, in part by the National Basic Research Program of China under Grant 2013CB329404, and in part by the NSF of Hubei Province under Grant 2011CDA003. Publisher copyright: {\textcopyright} 2014 IEEE.",

year = "2015",

month = mar,

doi = "10.1109/TNNLS.2014.2361026",

language = "English",

volume = "26",

pages = "628--639",

journal = "IEEE Transactions on Neural Networks and Learning Systems",

issn = "2162-237X",

publisher = "IEEE Computational Intelligence Society",

number = "3",

}

TY - JOUR

T1 - The generalization ability of online SVM classification based on Markov sampling

AU - Xu, Jie

AU - Yan Tang, Yuan

AU - Zou, Bin

AU - Xu, Zongben

AU - Li, Luoqing

AU - Lu, Yang

N1 - This work was supported in part by the National Science Foundation (NSF) of China under Project 11371007, Project 61370002, and Project 61403132, in part by the Multiyear Research, University of Macau, Macau, China, under Grant MYRG205(Y1-L4)-FST11-TYY and Grant MYRG187(Y1-L3)-FST11-TYY, in part by the Start-Up Research, University of Macau, under Grant SRG010-FST11-TYY, in part by the National Basic Research Program of China under Grant 2013CB329404, and in part by the NSF of Hubei Province under Grant 2011CDA003. Publisher copyright: © 2014 IEEE.

PY - 2015/3

Y1 - 2015/3

N2 - In this paper, we consider online support vector machine (SVM) classification learning algorithms with uniformly ergodic Markov chain (u.e.M.c.) samples. We establish the bound on the misclassification error of an online SVM classification algorithm with u.e.M.c. samples based on reproducing kernel Hilbert spaces and obtain a satisfactory convergence rate. We also introduce a novel online SVM classification algorithm based on Markov sampling, and present the numerical studies on the learning ability of online SVM classification based on Markov sampling for benchmark repository. The numerical studies show that the learning performance of the online SVM classification algorithm based on Markov sampling is better than that of classical online SVM classification based on random sampling as the size of training samples is larger.

AB - In this paper, we consider online support vector machine (SVM) classification learning algorithms with uniformly ergodic Markov chain (u.e.M.c.) samples. We establish the bound on the misclassification error of an online SVM classification algorithm with u.e.M.c. samples based on reproducing kernel Hilbert spaces and obtain a satisfactory convergence rate. We also introduce a novel online SVM classification algorithm based on Markov sampling, and present the numerical studies on the learning ability of online SVM classification based on Markov sampling for benchmark repository. The numerical studies show that the learning performance of the online SVM classification algorithm based on Markov sampling is better than that of classical online SVM classification based on random sampling as the size of training samples is larger.

KW - Generalization ability

KW - Markov sampling

KW - online support vector machine (SVM) classification

KW - uniformly ergodic Markov chain (u.e.M.c.).

UR - http://www.scopus.com/inward/record.url?scp=85027948646&partnerID=8YFLogxK

U2 - 10.1109/TNNLS.2014.2361026

DO - 10.1109/TNNLS.2014.2361026

M3 - Journal article

AN - SCOPUS:85027948646

SN - 2162-237X

VL - 26

SP - 628

EP - 639

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

IS - 3

ER -

The generalization ability of online SVM classification based on Markov sampling

Abstract

User-Defined Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this