Dimension-independent spectral gap of polar slice sampling
Preprint
Abstract
Polar slice sampling, a Markov chain construction for approximate sampling, performs, under suitable assumptions on the target and initial distribution, provably independent of the state space dimension. We extend the aforementioned result of Roberts & Rosenthal (2002) by developing a theory which identifies conditions, in terms of a generalized level set function, that imply an explicit lower bound on the spectral gap even in a general slice sampling context. Verifying the identified conditions for polar slice sampling yields a lower bound of 1/2 on the spectral gap for arbitrary dimension if the target density is rotationally invariant, log-concave along rays emanating from the origin and sufficiently smooth. The general theoretical result is potentially applicable beyond the polar slice sampling framework.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Convergence of hybrid slice sampling via spectral gapAdvances in Applied Probability, 2024
- Dimension‐independent Markov chain Monte Carlo on the sphereScandinavian Journal of Statistics, 2023
- Equivalences of Geometric Ergodicity of Markov ChainsJournal of Theoretical Probability, 2023
- Quantitative spectral gap estimate and Wasserstein contraction of simple slice samplingThe Annals of Applied Probability, 2021
- Batch means and spectral variance estimators in Markov chain Monte CarloThe Annals of Statistics, 2010
- The polar slice samplerStochastic Models, 2002
- Convergence of Slice Sampler Markov ChainsJournal of the Royal Statistical Society Series B: Statistical Methodology, 1999
- Geometric Ergodicity and Hybrid Markov ChainsElectronic Communications in Probability, 1997
- Spatial Statistics and Bayesian ComputationJournal of the Royal Statistical Society Series B: Statistical Methodology, 1993
- Central limit theorem for additive functionals of reversible Markov processes and applications to simple exclusionsCommunications in Mathematical Physics, 1986