Convergence of Sequential Monte Carlo Methods

By Arnaud Doucet, Nando de Freitas, Neil J. Gordon. 2007

1,265 citations recorded by the source corpus.

Subfields: Probabilistic & Bayesian Methods

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Probabilistic & Bayesian Methods

Citations in the corpus

Energy-Inspired Models: Learning with Sampler-Induced Distributions (2019, methodology): “…because | To ﬁrst order, the bound gap is related to the variance of this partition function estimator (e.g., [48]), which motivates sampling algorithms used in lower variance partition function estimators such as SMC [21] and AIS [52]. is an unbiased estimator of p ( x ) when z, ⇠ q ( z, | x ) .”
Stochastic variational inference (2012, background): “One exception is sequential Monte Carlo, although these typically lack strong convergence guarantees (Doucet et al., 2001).”
Kernel Sequential Monte Carlo (2015, background): “C O ] 25 J u l 2017 problems with a sequence of time-varying target distributions [9], e.g. in state-space models, where each intermediate distribution is typically deﬁned on a successively larger latent space.”
Learning Where to Attend with Deep Architectures for Image Tracking (2011, methodology): “The localization module is implemented as a particle filter (Doucet et al., 2001) which estimates the location, velocity and scale of the target object.”
Modified input estimation technique for tracking manoeuvring targets (2009, methodology): “Example 3: Since the performance of the proposed algorithm is presented as an estimation of the tracking of positions, velocities and accelerations, a comparison based on the Monte-Carlo simulation [28, 29] is also made to”
Particle filters for partially observed diffusions (2007, methodology): “There is a wide range of applications which fit in this framework; see Doucet et al. (2001) for references.”
Monte Carlo State-Space Likelihoods by Weighted Posterior Kernel Density Estimation (2004, methodology): “1), but the primary dif culty in practice is sample degradationas samples are lost in step 3 as t increases (Doucet et al. 2001b).”
Deep Probabilistic Programming (2017, methodology): “We benchmark runtimes for a ﬁxed number of Hamiltonian Monte Carlo ( HMC ; Neal, 2011) iterations on modern hardware: a 12-core Intel i7-5930K CPU at 3.50GHz and an NVIDIA Titan X (Maxwell) GPU.”
Bayesian State and Parameter Estimation of Uncertain Dynamical Systems (2006, methodology): “In the next section, we focus on stochastic simulation techniques for state estimation and use the term particle filters (PF) to denote the resulting algorithms (following the terminology of [18]), although similar algorithms have been called Monte Carlo filters [16] and sequential Monte Carlo Bayes”
Variational Sequential Monte Carlo (2017, methodology): “First, we show on simulated linear Gaussian SSM data that VSMC can outperform the (locally) optimal proposal [Doucet et al., 2001, Doucet and Johansen, 2009].”
Uncertainty assessment of hydrologic model states and parameters: Sequential data assimilation using the particle filter (2005, methodology): “Recent developments in sequential Monte Carlo (SMC) methods [Gordon et al., 1993; Fruhwirth-Schnatter, 1994; Cargnoni et al., 1997; Liu and Chen, 1998; Doucet et al., 2001; Pham, 2001; Arulampalam et al., 2002] now make the application of such methods attainable for the uncertainty assessment of h”
Gen: a general-purpose probabilistic programming system with programmable inference (2019, methodology): “Monte Carlo algorithms include rejection sampling, Markov chain Monte Carlo (MCMC), importance sampling, and sequential Monte Carlo (SMC) including particle filtering [15].”
Tree-Structured Recurrent Switching Linear Dynamical Systems for Multi-Scale Modeling (2018, methodology): “Bayesian state space models and inference algorithms enable posterior inference of the latent states of a system and the parameters that govern their dynamics (Särkkä, 2013; Barber et al., 2011; Doucet et al., 2001).”
Obstacles to High-Dimensional Particle Filtering (2008, background): “[See Gordon et al. (1993) or Doucet et al. (2001) for an introduction.]”