Particle Learning and Smoothing

2010/11/04 by Carlos M. Carvalho, Michael S. Johannes, Hedibert F. Lopes +1 · 1 citation
Mathematics · #stat.ME

paper · pdf · doi:10.1214/10-sts325

published as Statistical Science 2010, Vol. 25, No. 1, 88-106 · Published in at http://dx.doi.org/10.1214/10-STS325 the Statistical Science (http://www.imstat.org/sts/) by the Institute of Mathematical Statistics (http://www.imstat.org)

arxiv created 2010/11/04 · arxiv updated 2010/11/05

Abstract

Particle learning (PL) provides state filtering, sequential parameter learning and smoothing in a general class of state space models. Our approach extends existing particle methods by incorporating the estimation of static parameters via a fully-adapted filter that utilizes conditional sufficient statistics for parameters and/or states as particles. State smoothing in the presence of parameter uncertainty is also solved as a by-product of PL. In a number of examples, we show that PL outperforms existing particle filtering alternatives and proves to be a competitor to MCMC.

Cited by

• Particle filtering methods for partially observed branching processes

Related

• Learning nonlinear state-space models using smooth particle-filter-based\n likelihood approximations
• Differentiable Particle Filters: End-to-End Learning with Algorithmic Priors
• Learning to be Smooth: An End-to-End Differentiable Particle Smoother
• ILAPF: Incremental Learning Assisted Particle Filtering
• Particle Filter Made Simple: A Step-by-Step Beginner-friendly Guide