Incremental accelerated gradient methods for SVM classification: study of the constrained approach

Nicolas Couellan () and Sophie Jan

Computational Management Science, 2014, vol. 11, issue 4, 419-444

Abstract: We investigate constrained first order techniques for training support vector machines (SVM) for online classification tasks. The methods exploit the structure of the SVM training problem and combine ideas of incremental gradient technique, gradient acceleration and successive simple calculations of Lagrange multipliers. Both primal and dual formulations are studied and compared. Experiments show that the constrained incremental algorithms working in the dual space achieve the best trade-off between prediction accuracy and training time. We perform comparisons with an unconstrained large scale learning algorithm (Pegasos stochastic gradient) to emphasize that our choice can remain competitive for large scale learning due to the very special structure of the training problem. Copyright Springer-Verlag Berlin Heidelberg 2014

Keywords: Support vector machines; Kernel technique; Machine learning; Incremental gradient method; Accelerated gradient; Constrained gradient; Nonlinear programming; 65K05; 68T05; 90C20; 90C30; 90C90 (search for similar items in EconPapers)
Date: 2014
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1007/s10287-013-0186-2 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:comgts:v:11:y:2014:i:4:p:419-444

Ordering information: This journal article can be ordered from
http://www.springer. ... ch/journal/10287/PS2

DOI: 10.1007/s10287-013-0186-2

Access Statistics for this article

Computational Management Science is currently edited by Ruediger Schultz

More articles in Computational Management Science from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().