Comparer des méthodes

	Filtrage Séquentiel par Monte-Carlo pour Séries Temporelles	Échantillonnage de Gibbs
Domaine	Bayésien	Bayésien
Famille	Bayesian methods	Bayesian methods
Année d'origine	1993	1984
Auteur d'origine	Gordon, Salmond & Smith	Stuart Geman & Donald Geman
Type	Sequential Bayesian filtering algorithm	MCMC sampling algorithm
Source fondatrice	Gordon, N. J., Salmond, D. J., & Smith, A. F. M. (1993). Novel approach to nonlinear/non-Gaussian Bayesian state estimation. IEE Proceedings F — Radar and Signal Processing, 140(2), 107–113.	Geman, S. & Geman, D. (1984). Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 6(6), 721-741.
Alias	particle filter, time series SMC, sequential particle filtering, bootstrap particle filter	Gibbs sampler, coordinate-wise MCMC, systematic scan Gibbs, blocked Gibbs sampling
Apparentées	5	5
Résumé	Time series sequential Monte Carlo (SMC), commonly called the particle filter, is a Bayesian simulation method that tracks the hidden state of a dynamical system as observations arrive one at a time. A cloud of weighted random samples — particles — is propagated forward through the system dynamics, reweighted by how well each particle explains the new observation, and periodically resampled to keep the representation concentrated on plausible states.	Gibbs sampling is a Markov chain Monte Carlo algorithm that approximates a high-dimensional posterior distribution by repeatedly drawing each parameter from its full conditional distribution given all other parameters and the data. Because each draw is exact from a conditional — not a proposal that may be rejected — the sampler is efficient when those conditionals are available in closed form.