[2201.05002] Boost your favorite Markov Chain Monte Carlo sampler using Kac's theorem: the Kick-Kac teleportation algorithm
The present paper focuses on the problem of sampling from a given target distribution $\pi$ defined on some general state space. To this end, we introduce a novel class of non-reversible Markov chains, each chain being defined on an extended state space and having an invariant probability measure admitting $\pi$ as a marginal distribution. The proposed methodology is inspired by a new formulation of Kac's theorem and allows global and local dynamics to be smoothly combined. Under mild conditions, the corresponding Markov transition kernel can be shown to be irreducible and Harris recurrent. In addition, we establish that geometric ergodicity holds under appropriate conditions on the global and local dynamics. Finally, we illustrate numerically the use of the proposed method and its potential benefits in comparison to existing Markov chain Monte Carlo (MCMC) algorithms.
Boost your favorite Markov Chain Monte Carlo sampler using Kac’s theorem: the Kick-Kac teleportation algorithm Randal Douc1 , Alain Oliviero Durmus2 Aurélien Enfroy3 and Jimmy Olsson4 arXiv:2201.05002v2 [stat.CO] 13 May 2023 1 Department CITI, Telecom SudParis, Evry, France, e-mail: randal.douc@telecom-sudparis.eu…
saved by
related reading
- Dynamical Approach to RMT.pdfpeople.math.harvard.edu
- An optimization perspective on log-concave sampling and beyond | Sinho Chewichewisinho.github.io
- survey.dvimath.uchicago.edu
- High-Dimensional Gaussian Sampling: A Review and a Unifying Approach Based on a Stochastic Proximal Point Algorithmarxiv.org
- [2605.01172] A Theory of Generalization in Deep Learningarxiv.org
- Research • Leonid Petrov. Integrable Probabilitylpetrov.cc
- refining bounds - cover timesarxiv.org
- A Feynman-Kac Approach for the Spatial Derivative of the Solution to the Wick Stochastic Heat Equation Driven by Time Homogeneous White Noisearxiv.org
- [2010.02502] Denoising Diffusion Implicit Modelsarxiv.org
- Chapman–Kolmogorov equation - Wikipediaen.wikipedia.org
- [2011.01859] A Study of Policy Gradient on a Class of Exactly Solvable Modelsarxiv.org
- Analysis of Circulant Embedding Methods for Sampling Stationary Random Fieldsarxiv.org