Particle methods for maximum likelihood estimation in latent variable models

  • Authors:

  • Adam M. Johansen;Arnaud Doucet;Manuel Davy

  • Affiliations:

  • Department of Mathematics, University Walk, University of Bristol, Bristol, UK BS8 1TW;Department of Statistics & Department of Computer Science, University of British Columbia, Vancouver, Canada;LAGIS UMR 8146, Villeneuve d'Ascq Cedex, France 59651

  • Venue:
  • Statistics and Computing
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

Standard methods for maximum likelihood parameter estimation in latent variable models rely on the Expectation-Maximization algorithm and its Monte Carlo variants. Our approach is different and motivated by similar considerations to simulated annealing; that is we build a sequence of artificial distributions whose support concentrates itself on the set of maximum likelihood estimates. We sample from these distributions using a sequential Monte Carlo approach. We demonstrate state-of-the-art performance for several applications of the proposed approach.