Improving SMC Sampler Estimate by Recycling All Past Simulated Particles

Abstract : Sequential Monte Carlo (SMC) methods are not only a popular tool in the analysis of state-space models, but offer a powerful alternative to Markov chain Monte Carlo (MCMC) in situations where static Bayesian inference must be performed via simulation. In this paper, we propose a recycling scheme of all past simulated particles in the SMC sampler in order to reduce the variance of the final estimator. We demonstrate how the proposed approach outperforms the classi- cal strategy in two challenging models.
Complete list of metadatas

https://hal-imt.archives-ouvertes.fr/hal-01007551
Contributor : François Septier <>
Submitted on : Monday, June 16, 2014 - 6:15:15 PM
Last modification on : Thursday, February 21, 2019 - 10:34:10 AM

Identifiers

  • HAL Id : hal-01007551, version 1

Citation

Thi Le Thu Nguyen, François Septier, Gareth W. Peters, Yves Delignon. Improving SMC Sampler Estimate by Recycling All Past Simulated Particles. 2014 IEEE Workshop on Statistical Signal Processing (SSP 14), Jun 2014, Gold Coast, Australia. pp.1-4. ⟨hal-01007551⟩

Share

Metrics

Record views

273