Sequential Bayesian inference for implicit hidden Markov models and current limitations
From MaRDI portal
Abstract: Hidden Markov models can describe time series arising in various fields of science, by treating the data as noisy measurements of an arbitrarily complex Markov process. Sequential Monte Carlo (SMC) methods have become standard tools to estimate the hidden Markov process given the observations and a fixed parameter value. We review some of the recent developments allowing the inclusion of parameter uncertainty as well as model uncertainty. The shortcomings of the currently available methodology are emphasised from an algorithmic complexity perspective. The statistical objects of interest for time series analysis are illustrated on a toy "Lotka-Volterra" model used in population ecology. Some open challenges are discussed regarding the scalability of the reviewed methodology to longer time series, higher-dimensional state spaces and more flexible models.
Recommendations
- Bayesian estimation of hidden Markov chains: A stochastic implementation
- Bayesian inference for continuous-time hidden Markov models with an unknown number of states
- MCMC implementation for Bayesian hidden semi-Markov models with illustrative applications
- scientific article; zbMATH DE number 6276249
- Inference and Model Choice for Sequentially Ordered Hidden Markov Models
- Bayesian Inference of Hidden Markov Models Using Dirichlet Mixtures
- scientific article; zbMATH DE number 800790
- Bayesian Methods for Hidden Markov Models
Cites work
- A general framework for the parametrization of hierarchical models
- A nonasymptotic theorem for unnormalized Feynman-Kac particle models
- A sequential particle filter method for static models
- Approximate Bayesian computational methods
- Bayesian Inference for Linear Dynamic Models With Dirichlet Process Mixtures
- Bayesian model averaging: A tutorial. (with comments and a rejoinder).
- Biased online parameter inference for state-space models
- Bridging the ensemble Kalman and particle filters
- Can local particle filters beat the curse of dimensionality?
- Central limit theorem for sequential Monte Carlo methods and its application to Bayesian inference
- Efficient implementation of Markov chain Monte Carlo when using an unbiased likelihood estimator
- Efficient learning via simulation: a marginalized resample-move approach
- Establishing some order amongst exact approximations of MCMCs
- Following a moving target -- Monte Carlo inference for dynamic Bayesian models
- High-throughput scalable parallel resampling mechanism for effective redistribution of particles
- scientific article; zbMATH DE number 1666093 (Why is no real title available?)
- scientific article; zbMATH DE number 5919872 (Why is no real title available?)
- scientific article; zbMATH DE number 2117879 (Why is no real title available?)
- scientific article; zbMATH DE number 795289 (Why is no real title available?)
- Inference in hidden Markov models.
- On disturbance state-space models and the particle marginal Metropolis-Hastings sampler
- On parallel implementation of sequential Monte Carlo methods: the island particle model
- On particle Gibbs sampling
- On the role of interaction in sequential Monte Carlo algorithms
- On the stability of sequential Monte Carlo methods in high dimensions
- Optimal filtering and the dual process
- Particle approximations of the score and observed information matrix in state space models with application to parameter estimation
- Particle Gibbs with ancestor sampling
- Resampling algorithms and architectures for distributed particle filters
- Sequential Monte Carlo Methods in Practice
- Sequential Monte Carlo Samplers: Error Bounds and Insensitivity to Initial Conditions
- Simulating normalizing constants: From importance sampling to bridge sampling to path sampling
- Stability of Feynman-Kac formulae with path-dependent potentials
- Stability properties of some particle filters
- The Bayesian Choice
- Time series analysis via mechanistic models
- Uniform ergodicity of the particle Gibbs sampler
Cited in
(7)- Efficient \(\mathrm{SMC}^2\) schemes for stochastic kinetic models
- A New Method for Learning Imprecise Hidden Markov Models
- Parallel sequential Monte Carlo samplers and estimation of the number of states in a hidden Markov model
- Inference via low-dimensional couplings
- Smoothing with couplings of conditional particle filters
- Hidden Markov models for time series. An introduction using R
- Nested ensemble Kalman filter for static parameter inference in nonlinear state-space models
This page was built for publication: Sequential Bayesian inference for implicit hidden Markov models and current limitations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2786524)
