Feature Selection via Mathematical Programming

Feature Selection via Mathematical Programming (1997)

Cached

Download Links

[ftp.cs.wisc.edu]

by P.S. Bradley , O. L. Mangasarian , W. N. Street

Citations:

51 - 22 self

Versions

Version History

Metadata Version 2

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	Feature Selection via Mathematical Programming	user correction - Legacy Corrections
AUTHOR NAME	P.S. Bradley	user correction - Legacy Corrections
AUTHOR AFFIL	y	user correction - Legacy Corrections
AUTHOR NAME	O. L. Mangasarian	user correction - Legacy Corrections
AUTHOR NAME	W. N. Street	user correction - Legacy Corrections
AUTHOR AFFIL	; z; y; Computer Sciences Department, University of Wisconsin; z; Computer Science Department, 207 Mathematical Sciences, Oklahoma State University, Stillwater	user correction - Legacy Corrections
AUTHOR ADDR	; 1210 West Dayton Street, Madison, WI 53706,; OK 74078,	user correction - Legacy Corrections
ABSTRACT	The problem of discriminating between two finite point sets in n-dimensional feature space by a separating plane that utilizes as few of the features as possible, is formulated as a mathematical program with a parametric objective function and linear constraints. The step function that appears in the objective function can be approximated by a sigmoid or by a concave exponential on the nonnegative real line, or it can be treated exactly by considering the equivalent linear program with equilibrium constraints (LPEC). Computational tests of these three approaches on publicly available real-world databases have been carried out and compared with an adaptation of the optimal brain damage (OBD) method for reducing neural network complexity. One feature selection algorithm via concave minimization (FSV) reduced cross-validation error on a cancer prognosis database by 35.4% while reducing problem features from 32 to 4. Feature selection is an important problem in machine learning [18, 15, 1...	user correction - Legacy Corrections
YEAR	1997	user correction - Legacy Corrections
CITATIONS	36 found	ParsCit 1.0