Statistical Inference with Ensemble of Clustered Desparsified Lasso

Abstract : Medical imaging involves high-dimensional data, yet their acquisition is obtained for limited samples. Multivariate predictive models have become popular in the last decades to fit some external variables from imaging data, and standard algorithms yield point estimates of the model parameters. It is however challenging to attribute confidence to these parameter estimates, which makes solutions hardly trustworthy. In this paper we present a new algorithm that assesses parameters statistical significance and that can scale even when the number of predictors p ≥ 10^5 is much higher than the number of samples n ≤ 10^3 , by lever-aging structure among features. Our algorithm combines three main ingredients: a powerful inference procedure for linear models –the so-called Desparsified Lasso– feature clustering and an ensembling step. We first establish that Desparsified Lasso alone cannot handle n p regimes; then we demonstrate that the combination of clustering and ensembling provides an accurate solution, whose specificity is controlled. We also demonstrate stability improvements on two neuroimaging datasets.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01815255
Contributor : Jérôme-Alexis Chevalier <>
Submitted on : Wednesday, June 13, 2018 - 11:56:26 PM
Last modification on : Friday, March 22, 2019 - 1:24:48 AM
Long-term archiving on : Monday, September 17, 2018 - 12:34:47 PM

Files

miccai_2018.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01815255, version 1
  • ARXIV : 1806.05829

Citation

Jérôme-Alexis Chevalier, Joseph Salmon, Bertrand Thirion. Statistical Inference with Ensemble of Clustered Desparsified Lasso. MICCAI, 2018, Grenade, Spain. ⟨hal-01815255⟩

Share

Metrics

Record views

358

Files downloads

156