Speeding up parameter tuning for multi-class classification: A partial parametric path algorithm

Belen Martin-Barragan, Ling Liu, Francisco Javier Prieto

Research output: Contribution to conferenceAbstract

Abstract

The objective functions of Support Vector Machine methods (SVMs) often include parameters to weigh the relative importance of margins and training accuracy. For multi-class classification problems, in the presence of different misclassification costs, identifying a desirable set of values for these parameters is key for a good performance. We propose a partial parametric path algorithm, based on the property that the path of optimal solutions of the SVMs with respect to the preceding parameters is piecewise linear. This partial parametric path algorithm requires the solution of just one quadratic programming problem, and a number of linear systems of equations. Thus, it can significantly reduce the computational requirements of the algorithm. To systematically explore the different weights to assign to the misclassification costs, we combine the partial parametric path algorithm with a variable neighborhood search method. Our numerical experiments show the efficiency and reliability of the proposed partial parametric path algorithm. Furthermore through our numerical experiments we also verify the combination of partial parametric path algorithm and a variable neighborhood search method helps us to find a good set of parameters systematically.
Original languageEnglish
Publication statusPublished - 1 Dec 2016
Event9th International Conference of the ERCIM WG on Computational and Methodological Statistics - Higher Technical School of Engineering, University of Seville, Seville, Spain
Duration: 9 Dec 201611 Dec 2016
http://cmstatistics.org/CMStatistics2016/index.php

Conference

Conference9th International Conference of the ERCIM WG on Computational and Methodological Statistics
Abbreviated titleCFE-CMStatistics 2016
Country/TerritorySpain
CitySeville
Period9/12/1611/12/16
Internet address

Fingerprint

Dive into the research topics of 'Speeding up parameter tuning for multi-class classification: A partial parametric path algorithm'. Together they form a unique fingerprint.

Cite this