Non-asymptotic Error Bounds for Sequential MCMC Methods in Multimodal Settings
arXiv:1205.6733
Abstract
We prove non-asymptotic error bounds for Sequential MCMC methods in the case of multimodal target distributions. Our bounds depend in an explicit way on upper bounds on relative densities, on constants associated with local mixing properties of the MCMC dynamics, namely, local spectral gaps and local hyperboundedness, and on the amount of probability mass shifted between effectively disconnected components of the state space.
References in corpus (5)
- Central limit theorem for sequential Monte Carlo methods and its application to Bayesian inference
- Resolution exchange simulation
- Equi-energy sampler with applications in statistical inference and statistical mechanics
- Conditions for rapid mixing of parallel and simulated tempering on multimodal distributions
- Elementary bounds on Poincare and log-Sobolev constants for decomposable Markov chains