A non-asymptotic approach for model selection via penalization in high-dimensional mixture of experts models - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Electronic Journal of Statistics Year : 2022

A non-asymptotic approach for model selection via penalization in high-dimensional mixture of experts models

Abstract

Mixture of experts (MoE) are a popular class of statistical and machine learning models that have gained attention over the years due to their flexibility and efficiency. In this work, we consider Gaussian-gated localized MoE (GLoME) and block-diagonal covariance localized MoE (BLoME) regression models to present nonlinear relationships in heterogeneous data with potential hidden graph-structured interactions between high-dimensional predictors. These models pose difficult statistical estimation and model selection questions, both from a computational and theoretical perspective. This paper is devoted to the study of the problem of model selection among a collection of GLoME or BLoME models characterized by the number of mixture components, the complexity of Gaussian mean experts, and the hidden block-diagonal structures of the covariance matrices, in a penalized maximum likelihood estimation framework. In particular, we establish non-asymptotic risk bounds that take the form of weak oracle inequalities, provided that lower bounds for the penalties hold. The good empirical behavior of our models is then demonstrated on synthetic and real datasets.

Dates and versions

hal-03214606 , version 1 (02-05-2021)

Identifiers

Cite

Trungtin Nguyen, Hien Duy Nguyen, Faicel Chamroukhi, Florence Forbes. A non-asymptotic approach for model selection via penalization in high-dimensional mixture of experts models. Electronic Journal of Statistics , 2022, 16 (2), pp.4742 - 4822. ⟨10.1214/22-EJS2057⟩. ⟨hal-03214606⟩
110 View
0 Download

Altmetric

Share

Gmail Facebook X LinkedIn More