Efficient Optimization of Multi-class Support Vector Machines with MSVMpack - Archive ouverte HAL Access content directly
Conference Papers Year : 2015

Efficient Optimization of Multi-class Support Vector Machines with MSVMpack

Emmanuel Didiot
  • Function : Author
  • PersonId : 835404
Fabien Lauer

Abstract

In the field of machine learning, multi-class support vector machines (M-SVMs) are state-of-the-art classifiers with training algorithms that amount to convex quadratic programs. However, solving these quadratic programs in practice is a complex task that typically cannot be assigned to a general purpose solver. The paper describes the main features of an efficient solver for M-SVMs, as implemented in the MSVMpack software. The latest additions to this software are also highlighted and a few numerical experiments are presented to assess its efficiency.
Fichier principal
Vignette du fichier
DidiotLauerMCO15.pdf (295.15 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01134774 , version 1 (24-03-2015)

Identifiers

  • HAL Id : hal-01134774 , version 1

Cite

Emmanuel Didiot, Fabien Lauer. Efficient Optimization of Multi-class Support Vector Machines with MSVMpack. Modelling, Computation and Optimization in Information Systems and Management Sciences (MCO 2015), May 2015, Metz, France. ⟨hal-01134774⟩
98 View
127 Download

Share

Gmail Facebook X LinkedIn More