University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Optimal Feasible Step-size Based Working Set Selection for Large Scale SVMs Training

Peng, Shili, Hu, Qinghua, Dang, Jianwu and Wang, Wenwu (2020) Optimal Feasible Step-size Based Working Set Selection for Large Scale SVMs Training Neurocomputing.

[img] Text
PengHDW_Neurocomputing_2020_preprint.pdf - Accepted version Manuscript
Restricted to Repository staff only until 18 May 2022.

Download (448kB)


Effcient training of support vector machines (SVMs) with large-scale samples is of crucial importance in the era of big data. Sequential minimal optimization (SMO) is considered as an effective solution to this challenging task, and the working set selection is one of the key steps in SMO. Various strategies have been developed and implemented for working set selection in LibSVM and Shark. In this work we point out that the algorithm used in LibSVM does not maintain the box-constraints which, nevertheless, are very important for evaluating the final gain of the selection operation. Here, we propose a new algorithm to address this challenge. The proposed algorithm maintains the box-constraints within a selection procedure using a feasible optional step-size. We systematically study and compare several related algorithms, and derive new theoretical results. Experiments on benchmark data sets show that our algorithm effectively improves the training speed without loss of accuracy.

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
Peng, Shili
Hu, Qinghua
Dang, Jianwu
Date : 17 May 2020
Funders : National Natural Science Foundation of China (NSFC)
Uncontrolled Keywords : support vector machines, decomposition algorithm, working set selection, sequential minimal optimization, feasible step-size
Depositing User : James Marshall
Date Deposited : 01 Jun 2020 14:32
Last Modified : 01 Jun 2020 14:32

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800