Nonasymptotic analysis of adaptive and annealed Feynman-Kac particle models

DOI10.3150/14-BEJ680zbMATH Open1364.60131arXiv1209.5654OpenAlexW3098845144MaRDI QIDQ502900FDOQ502900

Authors: François Giraud, Pierre Del Moral 

Publication date: 11 January 2017

Published in: Bernoulli (Search for Journal in Brave)

Abstract: Sequential and quantum Monte Carlo methods, as well as genetic type search algorithms can be interpreted as a mean field and interacting particle approximations of Feynman-Kac models in distribution spaces. The performance of these population Monte Carlo algorithms is strongly related to the stability properties of nonlinear Feynman-Kac semigroups. In this paper, we analyze these models in terms of Dobrushin ergodic coefficients of the reference Markov transitions and the oscillations of the potential functions. Sufficient conditions for uniform concentration inequalities w.r.t. time are expressed explicitly in terms of these two quantities. We provide an original perturbation analysis that applies to annealed and adaptive Feynman-Kac models, yielding what seems to be the first results of this kind for these types of models. Special attention is devoted to the particular case of Boltzmann-Gibbs measures' sampling. In this context, we design an explicit way of tuning the number of Markov chain Monte Carlo iterations with temperature schedule. We also design an alternative interacting particle method based on an adaptive strategy to define the temperature increments. The theoretical analysis of the performance of this adaptive model is much more involved as both the potential functions and the reference Markov transitions now depend on the random evolution on the particle model. The nonasymptotic analysis of these complex adaptive models is an open research problem. We initiate this study with the concentration analysis of a simplified adaptive models based on reference Markov transitions that coincide with the limiting quantities, as the number of particles tends to infinity.

Full work available at URL: https://arxiv.org/abs/1209.5654

Recommendations

• On the convergence of quantum and sequential Monte Carlo methods
• A nonasymptotic theorem for unnormalized Feynman-Kac particle models
• On the concentration properties of interacting particle processes
• Mean field simulation for Monte Carlo integration
• Feynman-Kac particle integration with geometric interacting jumps

zbMATH Keywords

interacting particle systemssequential Monte Carlo methodsFeynman-Kac fomula

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Monte Carlo methods (65C05) Numerical analysis or methods applied to Markov chains (65C40) Interacting random processes; statistical mechanics type models; percolation theory (60K35) Stochastic particle methods (65C35)

Cited In (12)

• On the convergence of quantum and sequential Monte Carlo methods
• Annealed Feynman-Kac models
• A nonasymptotic theorem for unnormalized Feynman-Kac particle models
• Sequential ensemble transform for Bayesian inverse problems
• Robust measurement of (heavy-tailed) risks: theory and implementation
• Inference on high-dimensional implicit dynamic models using a guided intermediate resampling filter
• Tree based functional expansions for Feynman--Kac particle models
• Error estimates on ergodic properties of discretized Feynman-Kac semigroups
• Particle Filtering for Stochastic Navier--Stokes Signal Observed with Linear Additive Noise
• Mean field simulation for Monte Carlo integration
• A fast particle-based approach for calibrating a 3-D model of the Antarctic ice sheet
• Error bounds for sequential Monte Carlo samplers for multimodal distributions

This page was built for publication: Nonasymptotic analysis of adaptive and annealed Feynman-Kac particle models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q502900)