Randomized pick-freeze for sparse Sobol indices estimation in high dimension

Abstract : This article investigates a new procedure to estimate the influence of each variable of a given function defined on a high-dimensional space. More precisely, we are concerned with describing a function of a large number $p$ of parameters that depends only on a small number $s$ of them. Our proposed method is an unconstrained $\ell_{1}$-minimization based on the Sobol's method. We prove that, with only $\mathcal O(s\log p)$ evaluations of $f$, one can find which are the relevant parameters.
Liste complète des métadonnées

Cited literature [28 references]  Display  Hide  Download

https://hal.inria.fr/hal-00962473
Contributor : Alexandre Janon <>
Submitted on : Friday, March 21, 2014 - 1:03:06 PM
Last modification on : Thursday, January 11, 2018 - 6:26:42 AM
Document(s) archivé(s) le : Saturday, June 21, 2014 - 11:15:38 AM

Files

ArticleRandomPF_2014_03_17.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00962473, version 1
  • ARXIV : 1403.5537

Collections

Citation

Yohann de Castro, Alexandre Janon. Randomized pick-freeze for sparse Sobol indices estimation in high dimension. [Research Report] 2014. ⟨hal-00962473⟩

Share

Metrics

Record views

710

Files downloads

202