April, Tuesday 17th

14:30 (room 2014, 'Digiteo Shannon' 660 building) (see location)

Bertrand Thirion

(Parietal team, Neurospin, INRIA/CEA)

Title: Statistical inference for high-dimensional data & application to brain imaging


Medical imaging involves high-dimensional data, yet their
acquisition is obtained for limited samples. Multivariate predictive mod-
els 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 talk, I will present a new algorithm that assesses parameters
statistical significance and that can scale even when the number of predictors
p ≥ 100 000 is much higher than the number of samples n ≤ 1000 , by lever-
aging structure among features. Our algorithm combines three main in-
gredients: 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.

Contact: guillaume.charpiat at
All TAU seminars: here

Collaborateur(s) de cette page: guillaume .
Page dernièrement modifiée le Lundi 19 mars 2018 20:22:25 CET par guillaume.