Message Passing-Based Inference in the Gamma Mixture Model

Albert Podusenko; Bart van Erp; Dmitry Bagaev; İsmail Şenöz; Bert de Vries

doi:10.1109/MLSP52302.2021.9596329

Message Passing-Based Inference in the Gamma Mixture Model

Albert Podusenko, Bart van Erp, Dmitry Bagaev, İsmail Şenöz, Bert de Vries

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

3 Citations (Scopus)

1 Downloads (Pure)

Abstract

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.

Original language	English
Title of host publication	2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)
Publisher	Institute of Electrical and Electronics Engineers
Number of pages	6
ISBN (Electronic)	978-1-7281-6338-3
ISBN (Print)	978-1-6654-1184-4
DOIs	https://doi.org/10.1109/MLSP52302.2021.9596329
Publication status	Published - 15 Nov 2021
Event	31st IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2021 - Virtual, Gold Coast, Australia Duration: 25 Oct 2021 → 28 Oct 2021 Conference number: 31 https://2021.ieeemlsp.org/

Conference

Conference	31st IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2021
Abbreviated title	MLSP 2021
Country/Territory	Australia
City	Gold Coast
Period	25/10/21 → 28/10/21
Internet address	https://2021.ieeemlsp.org/

Keywords

Mixture models
Machine learning
Signal processing
Probabilistic logic
Mathematical models
Probability distribution
Gamma Mixture Model
Expectation-Maximization
Factor Graphs
Probabilistic Inference
Message Passing
Moment Matching

Access to Document

10.1109/MLSP52302.2021.9596329

Cite this

@inproceedings{868826663975434788a2ab3f2227e6bd,

title = "Message Passing-Based Inference in the Gamma Mixture Model",

abstract = "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.",

keywords = "Mixture models, Machine learning, Signal processing, Probabilistic logic, Mathematical models, Probability distribution, Gamma Mixture Model, Expectation-Maximization, Factor Graphs, Probabilistic Inference, Message Passing, Moment Matching",

author = "Albert Podusenko and {van Erp}, Bart and Dmitry Bagaev and İsmail {\c S}en{\"o}z and Vries, {Bert de}",

year = "2021",

month = nov,

day = "15",

doi = "10.1109/MLSP52302.2021.9596329",

language = "English",

isbn = "978-1-6654-1184-4",

booktitle = "2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "31st IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2021, MLSP 2021 ; Conference date: 25-10-2021 Through 28-10-2021",

url = "https://2021.ieeemlsp.org/",

}

Podusenko, A , van Erp, B , Bagaev, D , Şenöz, İ & Vries, BD 2021, Message Passing-Based Inference in the Gamma Mixture Model. in 2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)., 9596329, Institute of Electrical and Electronics Engineers, 31st IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2021, Gold Coast, Queensland, Australia, 25/10/21. https://doi.org/10.1109/MLSP52302.2021.9596329

Message Passing-Based Inference in the Gamma Mixture Model. / Podusenko, Albert ; van Erp, Bart ; Bagaev, Dmitry et al.
2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP). Institute of Electrical and Electronics Engineers, 2021. 9596329.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Message Passing-Based Inference in the Gamma Mixture Model

AU - Podusenko, Albert

AU - van Erp, Bart

AU - Bagaev, Dmitry

AU - Şenöz, İsmail

AU - Vries, Bert de

N1 - Conference code: 31

PY - 2021/11/15

Y1 - 2021/11/15

N2 - 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.

AB - 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.

KW - Mixture models

KW - Machine learning

KW - Signal processing

KW - Probabilistic logic

KW - Mathematical models

KW - Probability distribution

KW - Gamma Mixture Model

KW - Expectation-Maximization

KW - Factor Graphs

KW - Probabilistic Inference

KW - Message Passing

KW - Moment Matching

UR - http://www.scopus.com/inward/record.url?scp=85122794753&partnerID=8YFLogxK

U2 - 10.1109/MLSP52302.2021.9596329

DO - 10.1109/MLSP52302.2021.9596329

M3 - Conference contribution

SN - 978-1-6654-1184-4

BT - 2021 IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)

PB - Institute of Electrical and Electronics Engineers

T2 - 31st IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2021

Y2 - 25 October 2021 through 28 October 2021

ER -

Message Passing-Based Inference in the Gamma Mixture Model

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this