English

Approximating Posterior Predictive Distributions by Averaging Output From Many Particle Filters

Methodology 2021-02-16 v3 Machine Learning

Abstract

This paper introduces the {\it particle swarm filter} (not to be confused with particle swarm optimization): a recursive and embarrassingly parallel algorithm that targets an approximation to the sequence of posterior predictive distributions by averaging expectation approximations from many particle filters. A law of large numbers and a central limit theorem are provided, as well as an numerical study of simulated data from a stochastic volatility model.

Keywords

Cite

@article{arxiv.2006.15396,
  title  = {Approximating Posterior Predictive Distributions by Averaging Output From Many Particle Filters},
  author = {Taylor R. Brown},
  journal= {arXiv preprint arXiv:2006.15396},
  year   = {2021}
}