A partial graphical model with a structural prior on the direct links between predictors and responses - Archive ouverte HAL Access content directly
Journal Articles ESAIM: Probability and Statistics Year : 2021

A partial graphical model with a structural prior on the direct links between predictors and responses

Abstract

This paper is devoted to the estimation of a partial graphical model with a structural Bayesian penalization. Precisely, we are interested in the linear regression setting where the estimation is made through the direct links between potentially high-dimensional predictors and multiple responses, since it is known that Gaussian graphical models enable to exhibit direct links only, whereas coefficients in linear regressions contain both direct and indirect relations (due e.g. to strong correlations among the variables). A smooth penalty reflecting a generalized Gaussian Bayesian prior on the covariates is added, either enforcing patterns (like row structures) in the direct links or regulating the joint influence of predictors. We give a theoretical guarantee for our method, taking the form of an upper bound on the estimation error arising with high probability, provided that the model is suitably regularized. Empirical studies on synthetic data and a real dataset are conducted.
Fichier principal
Vignette du fichier
ps200072.pdf (2.34 Mo) Télécharger le fichier
Origin : Publication funded by an institution

Dates and versions

hal-03350930 , version 1 (21-09-2021)

Identifiers

Cite

Eunice Okome Obiang, Pascal Jézéquel, Frédéric Proïa. A partial graphical model with a structural prior on the direct links between predictors and responses. ESAIM: Probability and Statistics, 2021, 25, pp.298-324. ⟨10.1051/ps/2021010⟩. ⟨hal-03350930⟩
89 View
15 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More