Files and links (1)
SubmittedarXiv.org - Non-exclusive license to distribute, Open
Journal article
Mixing rates for Hamiltonian Monte Carlo algorithms in finite and infinite dimensions
Stochastic partial differential equations : analysis and computations, v 10(4), pp 1318-1391
01 Dec 2022
Abstract
We establish the geometric ergodicity of the preconditioned Hamiltonian Monte Carlo (HMC) algorithm defined on an infinite-dimensional Hilbert space, as developed in Beskos et al. (Stoch Process Appl 121(10):2201-2230, 2011). This algorithm can be used as a basis to sample from certain classes of target measures which are absolutely continuous with respect to a Gaussian measure. Our work addresses an open question posed in Beskos et al. (2011), and provides an alternative to a recent proof based on exact coupling techniques given in Bou-Rabee and Eberle (Two-scale coupling for preconditioned Hamiltonian Monte Carlo in infinite dimensions , 2019). The approach here establishes convergence in a suitable Wasserstein distance by using the weak Harris theorem together with a generalized coupling argument. We also show that a law of large numbers and central limit theorem can be derived as a consequence of our main convergence result. Moreover, our approach yields a novel proof of mixing rates for the classical finite-dimensional HMC algorithm. As such, the methodology we develop provides a flexible framework to tackle the rigorous convergence of other Markov Chain Monte Carlo algorithms. Additionally, we show that the scope of our result includes certain measures that arise in the Bayesian approach to inverse PDE problems, cf. Stuart (Acta Numer 19:451-559, 2010). Particularly, we verify all of the required assumptions for a certain class of inverse problems involving the recovery of a divergence free vector field from a passive scalar, Borggaard et al. (SIAM/ASA J Uncertain Quant 8(3):1036-1060, 2020).
Metrics
Details
- Title
- Mixing rates for Hamiltonian Monte Carlo algorithms in finite and infinite dimensions
- Creators
- Nathan E. Glatt-Holtz - Tulane UniversityCecilia F. Mondaini - Drexel University, Mathematics
- Publication Details
- Stochastic partial differential equations : analysis and computations, v 10(4), pp 1318-1391
- Publisher
- Springer Nature
- Number of pages
- 74
- Grant note
- 515990 / Simons Foundation travel grant
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Mathematics
- Web of Science ID
- WOS:000697073300001
- Scopus ID
- 2-s2.0-85115131301
- Other Identifier
- 991021876812604721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- Web of Science research areas
- Mathematics, Applied
- Statistics & Probability