Sequential Monte Carlo Methods in Practice

By Pradipta Sarkar. 2003

4,893 citations recorded by the source corpus.

Subfields: Statistics and Probability, 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 Statistics and Probability

In Probabilistic & Bayesian Methods

Citations in the corpus

Density Estimation in Infinite Dimensional Exponential Families (2013, methodology): “Similarly, in sampling methods such as sequential Monte Carlo (Doucet et al., 2001), it is often the case that the evaluation of unnormalized densities is sufficient to calculate required importance weights.”
Kernel Bayes' Rule (2010, methodology): “The KBR uses a weighted sample to represent the posterior; it is similar in this respect to sampling methods such as importance sampling and sequential Monte Carlo ([7]).”
Effective Bayesian Modeling of Groups of Related Count Time Series (2014, methodology): “The latent dynamics of {η`,t} and the observation model are the same as in the previous sections.”
P3O: Policy-on Policy-off Policy Optimization (2019, methodology): “This expression is a good rule of thumb and occurs, for instance, for a weighted average of Gaussian random variables (Quionero-Candela et al., 2009) or in particle ﬁltering (Smith, 2013).”
Learning Where to Attend with Deep Architectures for Image Tracking (2011, methodology): “The localization module is implemented with a particle ﬁlter (Doucet et al., 2001) which estimates the location, velocity and scale of the target object.”
A la Carte - Learning Fast Kernels (2014, methodology): “An alternative is to invert the cumulative distribution function and pick m locations equidistantly at locations This approach is commonly used in particle ﬁltering [Doucet et al., 2001].”
Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem (2022, positive): “In particle filtering, resampling steps (or branching mechanisms (Doucet et al., 2001, Chapter 2)) filter out particles with very small weights, and replace them with additional copies of particles with large weights.”
Venture: a higher-order probabilistic programming platform with programmable inference (2014, methodology): “This insight is at the heart of particle filtering, i.e. sequential importance sampling with resampling (Doucet et al., 2001), as well as more sophisticated sequential Monte Carlo techniques.”
BayesDB: A probabilistic programming system for querying the probable implications of data (2015, methodology): “1. incorporate(id = r , values = { ( c j , x ( r,c j ) ) } ) Each row is incorporated via a single Gibbs step that numerically marginalizes out all the latent variables associated with the row (Smith et al., 2013; Murphy, 2002).”
Robust localization using 3D NDT scan matching with experimentally determined uncertainty and road marker matching (2017, methodology): “In this study, we used the effective sample size (ESS) [22], and resampling is done when the following condition is satisfied: 1∑Np i=1(w 2 i ) 0.9, (7) where wi and Np denote the normalized likelihood of the i-th particle and number of particles, respectively.”
On the stability of sequential Monte Carlo methods in high dimensions (2011, methodology): “There are a wide variety of resampling techniques, and we refer the reader to [28] for details; in this article we only consider the multinomial method just described above.”
SV mixture models with application to S&P 500 index returns ☆ (2007, neutral): “Papers include Bontemps and Meddahi (2005), Duan (2003), Bai (2003), Hong and Li (2002), and Diebold, Gunther, and Tay (1998).”
Probabilistic machine learning and artificial intelligence (2015, background): “The fact that defining such universal inference algorithms for computer programs is even possible is somewhat surprising, but it is related to the generality of certain key ideas from sampling such as rejection sampling, sequential Monte Carlo methods 25 and ‘approximate Bayesian computation’ 49 .”
Learning to Infer Graphics Programs from Hand-Drawn Images (2017, methodology): “For added robustness as n becomes large, we treat the neural network outputs as proposals for a Sequential Monte Carlo (SMC) sampling scheme [11].”
Online Multiperson Tracking-by-Detection from a Single, Uncalibrated Camera (2011, methodology): “…filtering distribution can be approximated by Sequential Monte Carlo Estimation (or Particle Filtering), which represents the distribution with a set of weighted particles and consists of a dynamic model for prediction and an observation model to evaluate the likelihood of a predicted state [10].”
The vSLAM Algorithm for Robust Localization and Mapping (2005, methodology): “By also using a localization scheme with a particle filter [2] and an adaptive mixed proposal distribution [3], [5], vSLAM offers a breakthrough SLAM algorithm that allows navigation with good accuracy in various real-world environments.”