Feature selection for high dimensional regression using local search and statistical criteria

Julie Hamon 1, 2 Clarisse Dhaenens 1, 2 Gaël Even 3 Julien Jacques 4, 5
1 DOLPHIN - Parallel Cooperative Multi-criteria Optimization
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe
5 MODAL - MOdel for Data Analysis and Learning
Inria Lille - Nord Europe, LPP - Laboratoire Paul Painlevé - UMR 8524, CERIM - Santé publique : épidémiologie et qualité des soins-EA 2694, Polytech Lille - École polytechnique universitaire de Lille, Université de Lille, Sciences et Technologies
Abstract : Genomic selection is a genetic evaluation of animals from their DNA, based on a huge number of markers covering the whole genome. It requires advanced approaches and in particular feature selection methods. Feature selection is a combinatorial problem that may be addressed by combinatorial optimization methods. We propose to combine an iterated local search (ILS) with a statistical evaluation of a multivariate regression and we compared three criteria in order to analyse their impact on the performance of the local search.
Liste complète des métadonnées

Cited literature [6 references]  Display  Hide  Download

https://hal.inria.fr/hal-00749708
Contributor : Julie Hamon <>
Submitted on : Tuesday, March 5, 2013 - 9:25:24 AM
Last modification on : Thursday, February 21, 2019 - 10:52:49 AM
Document(s) archivé(s) le : Thursday, June 6, 2013 - 3:56:05 AM

File

julieHamon_meta2012.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00749708, version 2

Citation

Julie Hamon, Clarisse Dhaenens, Gaël Even, Julien Jacques. Feature selection for high dimensional regression using local search and statistical criteria. International Conference on Metaheuristics and Nature Inspired Computing, Oct 2012, Port El-Kantaoui, Tunisia. ⟨hal-00749708v2⟩

Share

Metrics

Record views

456

Files downloads

253