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

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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [13 references]  Display  Hide  Download

https://hal.inria.fr/hal-01026303
Contributor : Matthew Blaschko <>
Submitted on : Monday, July 21, 2014 - 12:22:12 PM
Last modification on : Tuesday, August 13, 2019 - 11:22:21 AM
Long-term archiving on : Monday, November 24, 2014 - 9:01:00 PM

File

MisyrlisSTMI2014.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01026303, version 1

Collections

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. ⟨hal-01026303⟩

Share

Metrics

Record views

376

Files downloads

531