Abstract | ||
---|---|---|
Metropolis algorithms for approximate sampling of probability measures on infinite dimensional Hilbert spaces are considered, and a generalization of the preconditioned Crank–Nicolson (pCN) proposal is introduced. The new proposal is able to incorporate information on the measure of interest. A numerical simulation of a Bayesian inverse problem indicates that a Metropolis algorithm with such a proposal performs independently of the state-space dimension and the variance of the observational noise. Moreover, a qualitative convergence result is provided by a comparison argument for spectral gaps. In particular, it is shown that the generalization inherits geometric convergence from the Metropolis algorithm with pCN proposal. |
Year | DOI | Venue |
---|---|---|
2018 | https://doi.org/10.1007/s10208-016-9340-x | Foundations of Computational Mathematics |
Keywords | Field | DocType |
Markov chain Monte Carlo,Metropolis algorithm,Spectral gap,Conductance,Bayesian inverse problem,Primary: 60J05,Secondary: 62F15,65C40 | Hilbert space,Convergence (routing),Rejection sampling,Mathematical optimization,Metropolis–Hastings algorithm,Probability measure,Inverse problem,Multiple-try Metropolis,Mathematics,Crank–Nicolson method | Journal |
Volume | Issue | ISSN |
18 | 2 | 1615-3375 |
Citations | PageRank | References |
2 | 0.47 | 4 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Daniel Rudolf | 1 | 2 | 0.47 |
Björn Sprungk | 2 | 7 | 2.12 |