Quantitative approximations of evolving probability measures and sequential Markov chain Monte Carlo methods
Feynman-Kac formulaFokker-Planck equationfunctional inequalitiesMarkov chain Monte Carlo methodMarkov processparticle systemsequential Monte Carlo methodspectral gap
Schrödinger and Feynman-Kac semigroups (47D08) Convergence of probability measures (60B10) Computational methods in Markov chains (60J22) Monte Carlo methods (65C05) Numerical analysis or methods applied to Markov chains (65C40) Interacting particle systems in time-dependent statistical mechanics (82C22) Stochastic methods (Fokker-Planck, Langevin, etc.) applied to problems in time-dependent statistical mechanics (82C31)
The main goal of the paper is to evaluate some non-asymptotic bounds for particle system approximations using an \(L^p\) approach in order to control the approximation error. The particle system dynamics is a combination of \(N\) independent Markov chain moves defined by the Markov processes \((X_t^N,P)\) with initial distribution \(\mu_0\). An approximation error -- of a function \(f:S\longrightarrow \mathbb{R}\) (\(S\) finite) with \(L^p\)-norm less than \(1\) -- is the difference \(<f,\nu_t^N>-<f,\mu_t>\), where \((\mu_t)_{t\geq 0}\) is a family of mutually absolutely continuous probability measures, and \(\nu_t^N\) is an empirical distribution of \((X_t^N,P)\). The main difference from other similar results in the domain is that this paper treats the case of \(N\) finite (non-asymptotic case) and time \(t\) continuous. The particle systems have the scope to discretize the evolution equations for probability measures (called Fokker-Planck equations). All original results obtained are summarized in Section 2 and establish non-asymptotic bounds for the variance of the estimator \(<f,\nu_t^N>\) in different situations (like global Poincaré and logarithmic Sobolev inequalities). The paper is technical, very hard to be followed by readers which do not know the domain. Two points can be emphasized here: 1. 50\% of the paper (3 sections and an appendix: 18 pages from 36) are dedicated to proofs. 2. Almost all results follow ideas and reasoning from \textit{P. Del Moral} and \textit{L. Miclo} [Séminaire de Probabilités XXXIV. Berlin: Springer. Lect. Notes Math. 1729, 1--145 (2000; Zbl 0963.60040)]. A similar approach of error bounds is developed for the discrete time by \textit{N. Schweizer} [Non-asymptotic error bounds for sequential MCMC methods. Ph.D. Thesis, Universität Bonn (2011)].
- \(L^p\) estimates for Feynman-Kac propagators with time-dependent reference measures
- A nonasymptotic theorem for unnormalized Feynman-Kac particle models
- A sequential particle filter method for static models
- Central limit theorem for sequential Monte Carlo methods and its application to Bayesian inference
- Curse-of-dimensionality revisited: Collapse of the particle filter in very large scale systems
- Equi-energy sampler with applications in statistical inference and statistical mechanics
- scientific article; zbMATH DE number 3478187 (Why is no real title available?)
- scientific article; zbMATH DE number 1236226 (Why is no real title available?)
- scientific article; zbMATH DE number 1069282 (Why is no real title available?)
- scientific article; zbMATH DE number 1500585 (Why is no real title available?)
- scientific article; zbMATH DE number 1358323 (Why is no real title available?)
- scientific article; zbMATH DE number 2106098 (Why is no real title available?)
- scientific article; zbMATH DE number 2117879 (Why is no real title available?)
- Inference in hidden Markov models.
- Limit theorems for weighted samples with applications to sequential Monte Carlo methods
- Minimum variance importance samplingviaPopulation Monte Carlo
- Monte Carlo strategies in scientific computing
- Non-asymptotic error bounds for sequential MCMC methods
- Non-autonomous Kato classes and Feynman--Kac propagators.
- On adaptive resampling strategies for sequential Monte Carlo methods
- On the Control of an Interacting Particle Estimation of Schrödinger Ground States
- On the Convergence and Applications of Generalized Simulated Annealing
- On the convergence of genetic algorithms -- a variational approach
- On the stability of interacting processes with applications to filtering and genetic algorithms
- On the stability of sequential Monte Carlo methods in high dimensions
- On the swapping algorithm
- Sequential Monte Carlo Methods in Practice
- Sequential Monte Carlo Samplers
- Sequential Monte Carlo Samplers: Error Bounds and Insensitivity to Initial Conditions
- Stability of sequential Markov Chain Monte Carlo methods
- Stability of sequential Monte Carlo samplers via the Foster-Lyapunov condition
- The cutoff phenomenon in finite Markov chains.
- Total variation cutoff in birth-and-death chains
- Error bounds for sequential Monte Carlo samplers for multimodal distributions
- Limit theorems for cloning algorithms
- Inference for a class of partially observed point process models
- Quantitative Approximation of the Probability Distribution of a Markov Process by Formal Abstractions
- scientific article; zbMATH DE number 2051225 (Why is no real title available?)
- Non-asymptotic error bounds for sequential MCMC methods
- Error bounds and normalising constants for sequential Monte Carlo samplers in high dimensions
- Finite sample complexity of sequential Monte Carlo estimators on multimodal target distributions
- Finite-sample complexity of sequential Monte Carlo estimators
- Quasi-Monte Carlo methods for Markov chains with continuous multi-dimensional state space
- \(L^p\) estimates for Feynman-Kac propagators with time-dependent reference measures
This page was built for publication: Quantitative approximations of evolving probability measures and sequential Markov chain Monte Carlo methods
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1950384)
