Dimension-independent Markov chain Monte Carlo on the sphere
arXiv:2112.12185 · doi:10.1111/sjos.12653
Abstract
We consider Bayesian analysis on high-dimensional spheres with angular central Gaussian priors. These priors model antipodally symmetric directional data, are easily defined in Hilbert spaces and occur, for instance, in Bayesian binary classification and level set inversion. In this paper we derive efficient Markov chain Monte Carlo methods for approximate sampling of posteriors with respect to these priors. Our approaches rely on lifting the sampling problem to the ambient Hilbert space and exploit existing dimension-independent samplers in linear spaces. By a push-forward Markov kernel construction we then obtain Markov chains on the sphere, which inherit reversibility and spectral gap properties from samplers in linear spaces. Moreover, our proposed algorithms show dimension-independent efficiency in numerical experiments.
arXiv comment38 pages, 8 figures
References in corpus (9)
- Geometric MCMC for Infinite-Dimensional Inverse Problems
- Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions
- Geodesic Monte Carlo on Embedded Manifolds
- Explicit error bounds for Markov chain Monte Carlo
- On a generalization of the preconditioned Crank-Nicolson Metropolis algorithm
- Nonasymptotic bounds on the estimation error of MCMC algorithms
- Rigorous confidence bounds for MCMC under a geometric drift condition
- Error bounds of MCMC for functions with unbounded stationary variance
- Computation of expectations by Markov chain Monte Carlo methods