Conference abstracts

Session B4 - Learning Theory

July 13, 17:30 ~ 17:55 - Room B6

On the Exponentially Weighted Aggregate with the Laplace Prior

Arnak Dalalyan

ENSAE/CREST, Universite Paris Saclay, France   -   arnak.dalalyan@ensae.fr

In this talk, we will present some results on the statistical behavior of the Exponentially Weighted Aggregate (EWA) in the problem of high-dimensional regression with fixed design. Under the assumption that the underlying regression vector is sparse, it is reasonable to use the Laplace distribution as a prior. The resulting estimator and, specifically, a particular instance of it referred to as the Bayesian lasso, was already used in the statistical literature because of its computational convenience, even though no thorough mathematical analysis of its statistical properties was carried out. We will present results that fill this gap by establishing sharp oracle inequalities for the EWA with the Laplace prior. These inequalities show that if the temperature parameter is small, the EWA with the Laplace prior satisfies the same type of oracle inequality as the lasso estimator does, as long as the quality of estimation is measured by the prediction loss. Extensions of the proposed methodology to the problem of prediction with low-rank matrices will be discussed as well.

Joint work with Edwin Grappin (ENSAE/CREST), Quentin Paris (HSE).

View abstract PDF



FoCM 2017, based on a nodethirtythree design.