Maximum Likelihood Infinite Mixture Distribution Estimation Utilizing Finite Gaussian Mixtures

Rafael Orellana, Rodrigo Carvajal, Juan C. Agüero

Research output: Contribution to journalArticlepeer-review

8 Scopus citations

Abstract

In this paper we develop a Maximum Likelihood estimation algorithm for the estimation of infinite mixture distributions. We assume a known conditional distribution, whilst the weighting distribution is assumed unknown and it is approximated by a finite Gaussian mixture. Our approach allows for the correct estimation of the Gaussian mixture parameters. We illustrate the estimation performance of our proposal with numerical simulations.

Original languageEnglish
Pages (from-to)706-711
Number of pages6
Journal18th IFAC Symposium on System Identification SYSID 2018: Stockholm, Sweden, 9-11 July 2018
Volume51
Issue number15
DOIs
StatePublished - 1 Jan 2018
Externally publishedYes

Keywords

  • Estimation
  • Expectation-Maximization
  • Gaussian Mixture
  • Maximum Likelihood
  • Optimization

Fingerprint

Dive into the research topics of 'Maximum Likelihood Infinite Mixture Distribution Estimation Utilizing Finite Gaussian Mixtures'. Together they form a unique fingerprint.

Cite this