On explicit L^2-convergence rate estimate for piecewise deterministic Markov processes in MCMC algorithms
From MaRDI portal
Publication:2135272
Abstract: We establish -exponential convergence rate for three popular piecewise deterministic Markov processes for sampling: the randomized Hamiltonian Monte Carlo method, the zigzag process, and the bouncy particle sampler. Our analysis is based on a variational framework for hypocoercivity, which combines a Poincar'{e}-type inequality in time-augmented state space and a standard energy estimate. Our analysis provides explicit convergence rate estimates, which are more quantitative than existing results.
The authors establish \(L^2\)-exponential convergence rate for three popular piecewise deterministic Markov processes for sampling: the randomized Hamiltonian Monte Carlo method, the zigzag process and the bouncy particle sampler. \newline The analysis is based on a variational framework for hypocoercivity, which combines a Poincaré-type inequality in time-augmented state space and a standard \(L^2\) energy estimate.\newline Explicit convergence rate estimates are provided, which are more quantitative than the existing results.
Recommendations
- Hypocoercivity of piecewise deterministic Markov process-Monte Carlo
- Polynomial convergence rates of piecewise deterministic Markov processes
- High-dimensional scaling limits of piecewise deterministic sampling algorithms
- Subgeometric hypocoercivity for piecewise-deterministic Markov process Monte Carlo methods
- Cores for piecewise-deterministic Markov processes used in Markov chain Monte Carlo
Cites work
- A Model for Collision Processes in Gases. I. Small Amplitude Processes in Charged and Neutral One-Component Systems
- Compact Sobolev imbeddings on finite measure spaces
- Coordinate sampler: a non-reversible Gibbs-like MCMC sampler
- Detailed spectral study of processes that are less hesistent than others
- Efficient posterior sampling for high-dimensional imbalanced logistic regression
- Ergodicity of the zigzag process
- Exponential ergodicity of the bouncy particle sampler
- Forward Event-Chain Monte Carlo: Fast Sampling by Randomness Control in Irreversible Markov Chains
- Geometric ergodicity of the bouncy particle sampler
- Geometric integrators and the Hamiltonian Monte Carlo method
- scientific article; zbMATH DE number 3901778 (Why is no real title available?)
- Hypocoercivity
- Hypocoercivity and exponential time decay for the linear inhomogeneous relaxation Boltzmann equation
- Hypocoercivity for kinetic equations with linear relaxation terms
- Hypocoercivity for Kolmogorov backward evolution equations and applications
- Hypocoercivity for linear kinetic equations conserving mass
- Hypocoercivity of piecewise deterministic Markov process-Monte Carlo
- Hypoelliptic second order differential equations
- Low-lying eigenvalues and convergence to the equilibrium of some piecewise deterministic Markov processes generators in the small temperature regime
- Non-reversible Metropolis-Hastings
- 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
- Piecewise deterministic simulated annealing
- Quantitative perturbative study of convergence to equilibrium for collisional kinetic models in the torus
- Randomized Hamiltonian Monte Carlo
- Randomized Hamiltonian Monte Carlo as scaling limit of the bouncy particle sampler and dimension-free convergence rates
- Spectral methods for Langevin dynamics and associated error estimates
- Stochastic processes and applications. Diffusion processes, the Fokker-Planck and Langevin equations
- 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
Cited in
(24)- Subgeometric hypocoercivity for piecewise-deterministic Markov process Monte Carlo methods
- Cores for piecewise-deterministic Markov processes used in Markov chain Monte Carlo
- Mixing time guarantees for unadjusted Hamiltonian Monte Carlo
- Complexity of zigzag sampling algorithm for strongly log-concave distributions
- Spectral analysis of the zigzag process
- A short introduction to piecewise deterministic Markov samplers
- Low-lying eigenvalues and convergence to the equilibrium of some piecewise deterministic Markov processes generators in the small temperature regime
- Hypocoercivity of piecewise deterministic Markov process-Monte Carlo
- Fast L₂-approximation of integral-type functionals of Markov processes
- scientific article; zbMATH DE number 2166046 (Why is no real title available?)
- Birth–death dynamics for sampling: global convergence, approximations and their asymptotics
- Polynomial convergence rates of piecewise deterministic Markov processes
- An entropic approach for Hamiltonian Monte Carlo: the idealized case
- Variational methods for the kinetic Fokker-Planck equation
- Non-reversible lifts of reversible diffusion processes and relaxation times
- Hypocoercivity meets lifts
- L^2-exponential ergodicity of stochastic Hamiltonian systems with -stable Lévy noises
- Unadjusted Hamiltonian MCMC with stratified Monte Carlo time integration
- HMC and underdamped Langevin united in the unadjusted convex smooth case
- Windowed thinning and query complexity for the bouncy particle and Zigzag samplers
- Exact simulation of diffusions and improved algorithms for log-concave sampling
- GIST: Gibbs self-tuning for locally adaptive Hamiltonian Monte Carlo
- Space-time divergence lemmas and optimal non-reversible lifts of diffusions on Riemannian manifolds with boundary
- Unbiased kinetic Langevin Monte Carlo with inexact gradients
This page was built for publication: On explicit \(L^2\)-convergence rate estimate for piecewise deterministic Markov processes in MCMC algorithms
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2135272)
