Data Files to Accompany "The Support Vector Machine and Mixed Integer Linear Programming: Ramp Loss SVM with L1-Norm Regularization"

Authors

Eric J. Hess, Virginia Commonwealth UniversityFollow
J. Paul Brooks, Virginia Commonwealth UniversityFollow

Document Type

Dataset

Publication Date

2014

Description

96 data files in CPLEX LP format, presented in a zip file as the primary download and individually as supplemental content.

Abstract

These files accompany, "The Support Vector Machine and Mixed Integer Linear Programming: Ramp Loss SVM with L1-Norm Regularization" by Eric J. Hess and J. Paul Brooks, presented at the 2015 INFORMS Computing Society Conference, Operations Research and Computing: Algorithms and Software for Analytics, Richmond, Virginia January 11-13, 2015.

The files contain instances of optimization problems that are described in the paper and for which results are reported. The files are in CPLEX LP format. The naming convention of the files is as follows: ndBTj0F.lp, where is the number of samples, is the number of attributes, and refers to the mathematical programming formulation. The key for the formulation is 1 - SVMIP1-RL, 2 - SVMIP2-RL, 3 - GSVM1-RL, 4 - GSVM2-RL, 5 - MILPSVM-RL, 6 - rSVM-RL, 10 - SVM, 11 - GSVM1, 12 - GSVM2, 13 - LPSVM, 14 - rSVM.

File Format

CPLEX LP

Rights

CC-BY http://creativecommons.org/licenses/by/2.0/

Is Part Of

VCU Statistical Sciences and Operations Research Data

Date of Submission

11-21-2014