Speeding-up model-selection in GraphNet via early-stopping and univariate feature-screening

Abstract : The GraphNet (aka S-Lasso), as well as other " spar-sity + structure " priors like TV-L1, are not easily applicable to brain data because of technical problems concerning the selection of the regularization parameters. Also, in their own right, such models lead to challenging high-dimensional optimization problems. In this manuscript, we present some heuristics for speeding up the overall optimization process: (a) Early-stopping, whereby one halts the optimization process when the test score (performance on leftout data) for the internal cross-validation for model-selection stops improving, and (b) univariate feature-screening, whereby irrelevant (non-predictive) voxels are detected and eliminated before the optimization problem is entered, thus reducing the size of the problem. Empirical results with GraphNet on real MRI (Magnetic Resonance Imaging) datasets indicate that these heuristics are a win-win strategy, as they add speed without sacrificing the quality of the predictions. We expect the proposed heuristics to work on other models like TV-L1, etc.
Liste complète des métadonnées

Cited literature [19 references]  Display  Hide  Download

https://hal.inria.fr/hal-01147731
Contributor : Elvis Dohmatob <>
Submitted on : Friday, July 3, 2015 - 1:37:26 PM
Last modification on : Friday, March 8, 2019 - 1:20:19 AM
Document(s) archivé(s) le : Friday, October 9, 2015 - 5:30:38 PM

File

paper.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01147731, version 1

Citation

Elvis Dohmatob, Michael Eickenberg, Bertrand Thirion, Gaël Varoquaux. Speeding-up model-selection in GraphNet via early-stopping and univariate feature-screening. PRNI, Jun 2015, Stanford, United States. ⟨hal-01147731⟩

Share

Metrics

Record views

968

Files downloads

385