Approximations of conditional probability density functions in Lebesgue spaces via mixture of experts models

Hien Duy Nguyen (), TrungTin Nguyen, Faicel Chamroukhi and Geoffrey John McLachlan
Additional contact information
Hien Duy Nguyen: La Trobe University
TrungTin Nguyen: Normandie Univ, UNICAEN, CNRS, LMNO
Faicel Chamroukhi: Normandie Univ, UNICAEN, CNRS, LMNO
Geoffrey John McLachlan: School of Mathematics and Physics, University of Queensland

Journal of Statistical Distributions and Applications, 2021, vol. 8, issue 1, 1-15

Abstract: Abstract 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 denseness results in Lebesgue spaces, when inputs and outputs variables are both compactly supported. We further prove an almost uniform convergence result when the input is univariate. Auxiliary lemmas are proved regarding the richness of the soft-max gating function class, and their relationships to the class of Gaussian gating functions.

Keywords: Mixture of experts; Conditional probability density functions; Approximation theory; Mixture models; Lebesgue spaces (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://link.springer.com/10.1186/s40488-021-00125-0 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:jstada:v:8:y:2021:i:1:d:10.1186_s40488-021-00125-0

Ordering information: This journal article can be ordered from
http://www.springer.com/statistics/journal/40488

DOI: 10.1186/s40488-021-00125-0

Access Statistics for this article

Journal of Statistical Distributions and Applications is currently edited by Felix Famoye and Carl Lee

More articles in Journal of Statistical Distributions and Applications from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().