Predicting cross-task behavioral variables from fMRI data using the k-support norm

Michail Misyrlis 1, 2 Anna Konova 2, 3 Matthew Blaschko 4, 5 Jean Honorio 6 Nelly Alia-Klein 2 Rita Goldstein 2 Dimitris Samaras 3
1 Computer Science Department [SUNY]
2 Mount Sinai School of Medicine
3 SBU - Stony Brook University [The State University of New York]
4 GALEN - Organ Modeling through Extraction, Representation and Understanding of Medical Image Content
Inria Saclay - Ile de France, Ecole Centrale Paris
5 CVN - Centre de vision numérique
6 CSAIL - Computer Science and Artificial Intelligence Laboratory [Cambridge]
Abstract : Sparsity regularization allows handling the curse of dimensionality, a problem commonly found in fMRI data. In this paper, we compare LASSO (L1 regularization) and the recently introduced k-support norm on their ability to predict real valued variables from brain fMRI data for cocaine addiction, in a principled model selection setting. Furthermore, in the context of those two regularization methods, we compare two loss functions: squared loss and absolute loss. With the squared loss function, k-support norm outperforms LASSO in predicting real valued behavioral variables measured in an inhibitory control task given fMRI data from a different task, designed to capture emotionally-salient reward. The absolute loss function leads to significantly better predictive performance for both methods in almost all cases and the k-support norm leads to more interpretable and more stable solutions often by an order of magnitude. Our results support the use of the k-support norm for fMRI analysis and the generalizability of the I-RISA model of cocaine addiction.
Type de document :
Communication dans un congrès
Sparsity Techniques in Medical Imaging (STMI), Sep 2014, Boston, United States. 2014
Liste complète des métadonnées

Littérature citée [13 références]  Voir  Masquer  Télécharger
https://hal.inria.fr/hal-01026303
Contributeur : Matthew Blaschko <>
Soumis le : lundi 21 juillet 2014 - 12:22:12
Dernière modification le : vendredi 6 avril 2018 - 13:32:01
Document(s) archivé(s) le : lundi 24 novembre 2014 - 21:01:00

Fichier

MisyrlisSTMI2014.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01026303, version 1

Collections

INRIA | EC-PARIS | CVN

Citation

Michail Misyrlis, Anna Konova, Matthew Blaschko, Jean Honorio, Nelly Alia-Klein, et al.. Predicting cross-task behavioral variables from fMRI data using the k-support norm. Sparsity Techniques in Medical Imaging (STMI), Sep 2014, Boston, United States. 2014. 〈hal-01026303〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

328

Téléchargements de fichiers

312

Contact


archive-ouverte@inria.fr