172 citations · 664 across the 34 of their papers we have counts for
6 papers · 1 filter
Non-asymptotic model selection in block-diagonal mixture of polynomial experts models
TrungTin Nguyen, Faicel Chamroukhi, Hien Duy Nguyen +1
Model selection, via penalized likelihood type criteria, is a standard task in many statistical inference and machine learning problems. Progress has led to deriving criteria with…
A non-asymptotic approach for model selection via penalization in high-dimensional mixture of experts models
TrungTin Nguyen, Hien Duy Nguyen, Faicel Chamroukhi +1
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 w…
Approximations of conditional probability density functions in Lebesgue spaces via mixture of experts models
Hien Duy Nguyen, TrungTin Nguyen, Faicel Chamroukhi +1
Mixture of experts (MoE) models are widely applied for conditional probability density estimation problems. We demonstrate the richness of the class of MoE models by proving densen…
Non-asymptotic oracle inequalities for the Lasso in high-dimensional mixture of experts
TrungTin Nguyen, Hien D Nguyen, Faicel Chamroukhi +1
We investigate the estimation properties of the mixture of experts (MoE) model in a high-dimensional setting, where the number of predictors is much larger than the sample size, an…
Approximation of probability density functions via location-scale finite mixtures in Lebesgue spaces
TrungTin Nguyen, Faicel Chamroukhi, Hien D Nguyen +1
The class of location-scale finite mixtures is of enduring interest both from applied and theoretical perspectives of probability and statistics. We prove the following results: to…
Approximation by finite mixtures of continuous density functions that vanish at infinity
T Tin Nguyen, Hien D Nguyen, Faicel Chamroukhi +1
Given sufficiently many components, it is often cited that finite mixture models can approximate any other probability density function (pdf) to an arbitrary degree of accuracy. Un…