Elements of sequential Monte Carlo

DOI10.1561/2200000074MaRDI QIDQ5213202zbMATH OpenOpenAlexWikidataFDO

Authors Christian A. Naesseth, Fredrik Lindsten, Thomas B. Schön

Publication date 31 January 2020

Published in Foundations and Trends® in Machine Learning (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1903.04797

zbMATH Keywords

Bayesian learninglearningsamplingstatistical methods

Mathematics Subject Classification ID

Bayesian inference (62F15) Monte Carlo methods (65C05) Research exposition (monographs, survey articles) pertaining to computer science (68-02) Learning and adaptive systems in artificial intelligence (68T05)

Abstract: A core problem in statistics and probabilistic machine learning is to compute probability distributions and expectations. This is the fundamental problem of Bayesian statistics and machine learning, which frames all inference as expectations with respect to the posterior distribution. The key challenge is to approximate these intractable expectations. In this tutorial, we review sequential Monte Carlo (SMC), a random-sampling-based class of methods for approximate inference. First, we explain the basics of SMC, discuss practical issues, and review theoretical results. We then examine two of the main user design choices: the proposal distributions and the so called intermediate target distributions. We review recent results on how variational inference and amortization can be used to learn efficient proposals and target distributions. Next, we discuss the SMC estimate of the normalizing constant, how this can be used for pseudo-marginal inference and inference evaluation. Throughout the tutorial we illustrate the use of SMC on various models commonly used in machine learning, such as stochastic recurrent neural networks, probabilistic graphical models, and probabilistic programs.

Recommendations

• Sequential Monte Carlo Samplers
• Controlled sequential Monte Carlo
• scientific article; zbMATH DE number 5007617
• Sequential Monte Carlo samplers with independent Markov chain Monte Carlo proposals
• An introduction to sequential Monte Carlo

Cited in

(15)

• Simple conditions for convergence of sequential Monte Carlo genealogies with applications
• Correctness of sequential Monte Carlo inference for probabilistic programming languages
• Sequential Monte Carlo with transformations
• Lookahead strategies for sequential Monte Carlo
• Sequential Monte Carlo Methods in Practice
• Learning undirected graphical models using persistent sequential Monte Carlo
• scientific article; zbMATH DE number 5007617 (Why is no real title available?)
• Target-aware Bayesian inference: how to beat optimal conventional estimators
• Variational objectives for Markovian dynamics with backward simulation
• Sequential Monte Carlo Methods for Statistical Analysis of Tables
• Properties of marginal sequential Monte Carlo methods
• Automatic alignment in higher-order probabilistic programming languages
• A switching state-space transmission model for tracking epidemics and assessing interventions
• Learning dynamical systems with particle stochastic approximation EM
• String diagrams with factorized densities

This page was built for publication: Elements of sequential Monte Carlo

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5213202)