Message Passing-Based Inference in the Gamma Mixture Model

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

Samenvatting

The Gamma mixture model is a flexible probability distribution for representing beliefs about scale variables such as precisions. Inference in the Gamma mixture model for all latent variables is non-trivial as it leads to intractable equations. This paper presents two variants of variational message passing-based inference in a Gamma mixture model. We use moment matching and alternatively expectation-maximization to approximate the posterior distributions. The proposed method supports automated inference in factor graphs for large probabilistic models that contain multiple Gamma mixture models as plug-in factors. The Gamma mixture model has been implemented in a factor graph package and we present experimental results for both synthetic and real-world data sets.
Originele taal-2Engels
Titel2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)
UitgeverijInstitute of Electrical and Electronics Engineers
Aantal pagina's6
ISBN van elektronische versie978-1-7281-6338-3
ISBN van geprinte versie978-1-6654-1184-4
DOI's
StatusGepubliceerd - 15 nov 2021
Evenement31st IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2021 - Virtual, Gold Coast, Australië
Duur: 25 okt 202128 okt 2021
Congresnummer: 31
https://2021.ieeemlsp.org/

Congres

Congres31st IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2021
Verkorte titelMLSP 2021
Land/RegioAustralië
StadGold Coast
Periode25/10/2128/10/21
Internet adres

Vingerafdruk

Duik in de onderzoeksthema's van 'Message Passing-Based Inference in the Gamma Mixture Model'. Samen vormen ze een unieke vingerafdruk.

Citeer dit