Abstract: Zig-Zag is Piecewise Deterministic Markov Process, efficiently used for simulation in an MCMC setting. As we show in this article, it fails to be exponentially ergodic on heavy tailed target distributions. We introduce an extension of the Zig-Zag process by allowing the process to move with a non-constant speed function , depending on the current state of the process. We call this process Speed Up Zig-Zag (SUZZ). We provide conditions that guarantee stability properties for the SUZZ process, including non-explosivity, exponential ergodicity in heavy tailed targets and central limit theorem. Interestingly, we find that using speed functions that induce explosive deterministic dynamics may lead to stable algorithms that can even mix faster. We further discuss the choice of an efficient speed function by providing an efficiency criterion for the one-dimensional process and we support our findings with simulation results.
Recommendations
Cites work
- A Liapounov bound for solutions of the Poisson equation
- A note on the polynomial ergodicity of the one-dimensional Zig-Zag process
- A piecewise deterministic Monte Carlo method for diffusion bridges
- A piecewise deterministic scaling limit of lifted Metropolis-Hastings in the Curie-Weiss model
- A stochastic model related to the telegrapher's equation
- Accelerating Gaussian diffusions
- Accelerating reversible Markov chains
- Analysis of a nonreversible Markov chain sampler.
- Automatic zig-zag sampling in practice
- Equation of state calculations by fast computing machines
- Ergodicity of the zigzag process
- Exponential convergence of Langevin distributions and their discrete approximations
- Fluctuations in Markov processes. Time symmetry and martingale approximation.
- Geometric ergodicity of Metropolis algorithms
- Glauber dynamics for the mean-field Ising model: cut-off, critical power law, and metastability
- scientific article; zbMATH DE number 3901778 (Why is no real title available?)
- scientific article; zbMATH DE number 3951715 (Why is no real title available?)
- scientific article; zbMATH DE number 646825 (Why is no real title available?)
- Irreversible Monte Carlo algorithms for efficient sampling
- Large deviations for the empirical measure of the zig-zag process
- Limit theorems for the zig-zag process
- Long time behavior of telegraph processes under convex potentials
- Markov Chain Monte Carlo Convergence Diagnostics: A Comparative Review
- Markov Chains and Stochastic Stability
- Non-reversible Metropolis-Hastings
- ON DIFFUSION BY DISCONTINUOUS MOVEMENTS, AND ON THE TELEGRAPH EQUATION
- On the geometric ergodicity of Hamiltonian Monte Carlo
- Optimal non-reversible linear drift for the convergence to equilibrium of a diffusion
- Partially collapsed Gibbs sampling and path-adaptive Metropolis-Hastings in high-energy astrophysics
- Piecewise deterministic Markov processes and their invariant measures
- Piecewise deterministic Markov processes for continuous-time Monte Carlo
- Piecewise deterministic Markov processes for scalable Monte Carlo on restricted domains
- Quantitative estimates for the long-time behavior of an ergodic variant of the telegraph process
- Simulation of nonhomogeneous poisson processes by thinning
- Spectral analysis of the zigzag process
- Stability of Markovian processes II: continuous-time processes and sampled chains
- Stability of Markovian processes III: Foster–Lyapunov criteria for continuous-time processes
- Subgeometric hypocoercivity for piecewise-deterministic Markov process Monte Carlo methods
- The Bouncy Particle Sampler: A Non-Reversible Rejection-Free Markov Chain Monte Carlo Method
- The zig-zag process and super-efficient sampling for Bayesian analysis of big data
- Variable transformation to obtain geometric ergodicity in the random-walk Metropolis algorithm
- Variance reduction using nonreversible Langevin samplers
Cited in
(5)
This page was built for publication: Speed up Zig-Zag
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6138921)
