Randomized Hamiltonian Monte Carlo as scaling limit of the bouncy particle sampler and dimension-free convergence rates
From MaRDI portal
Publication:2075323
DOI10.1214/20-AAP1659zbMath1484.65004arXiv1808.04299OpenAlexW2886027640WikidataQ114060532 ScholiaQ114060532MaRDI QIDQ2075323
Daniel Paulin, Alexandre Bouchard-Côté, Arnaud Doucet, George Deligiannidis
Publication date: 14 February 2022
Published in: The Annals of Applied Probability (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1808.04299
Computational methods in Markov chains (60J22) Continuous-time Markov processes on general state spaces (60J25) Monte Carlo methods (65C05) Functional limit theorems; invariance principles (60F17)
Related Items (9)
On explicit \(L^2\)-convergence rate estimate for piecewise deterministic Markov processes in MCMC algorithms ⋮ Hypocoercivity with Schur complements ⋮ Connecting the Dots: Numerical Randomized Hamiltonian Monte Carlo with State-Dependent Event Rates ⋮ Couplings for Andersen dynamics ⋮ Exact targeting of Gibbs distributions using velocity-jump processes ⋮ Gradient-Based Markov Chain Monte Carlo for Bayesian Inference With Non-differentiable Priors ⋮ Randomized time Riemannian manifold Hamiltonian Monte Carlo ⋮ Uncertainty Quantification for Markov Processes via Variational Principles and Functional Inequalities ⋮ Ergodicity of the zigzag process
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- The Zig-Zag Process and Super-Efficient Sampling for Bayesian Analysis of Big Data
- The Bouncy Particle Sampler: A Non-Reversible Rejection-Free Markov Chain Monte Carlo Method
- Diffusion limits of the random walk Metropolis algorithm in high dimensions
- Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions
- Ricci curvature of Markov chains on metric spaces
- Introduction to Hamiltonian dynamical systems and the \(N\)-body problem.
- A simple proof of the Poincaré inequality for a large class of probability measures
- An Efron-Stein inequality for nonsymmetric statistics
- On extensions of the Brunn-Minkowski and Prekopa-Leindler theorems, including inequalities for log concave functions, and with an application to the diffusion equation
- Exponential convergence of Langevin distributions and their discrete approximations
- Weak convergence and optimal scaling of random walk Metropolis algorithms
- Slice sampling. (With discussions and rejoinder)
- Piecewise deterministic Markov processes for scalable Monte Carlo on restricted domains
- Randomized Hamiltonian Monte Carlo
- Hypoelliptic estimates and spectral theory for Fokker-Planck operators and Witten Laplacians
- From Metropolis to diffusions: Gibbs states and optimal scaling.
- Geometric ergodicity and the spectral gap of non-reversible Markov chains
- A piecewise deterministic scaling limit of lifted Metropolis-Hastings in the Curie-Weiss model
- Optimal scaling of random-walk Metropolis algorithms on general target distributions
- Mixing of Hamiltonian Monte Carlo on strongly log-concave distributions: continuous dynamics
- Hypocoercivity of piecewise deterministic Markov process-Monte Carlo
- Hierarchical models and tuning of random walk Metropolis algorithms
- Ergodicity of the zigzag process
- Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
- Exponential ergodicity of the bouncy particle sampler
- Optimal tuning of the hybrid Monte Carlo algorithm
- Weak convergence of Metropolis algorithms for non-I.I.D. target distributions
- Hypocoercive relaxation to equilibrium for some kinetic models
- Lévy matters III. Lévy-type processes: construction, approximation and sample path properties
- Coupling and convergence for Hamiltonian Monte Carlo
- Geometric ergodicity of the bouncy particle sampler
- Piecewise deterministic simulated annealing
- Stability and Ergodicity of Piecewise Deterministic Markov Processes
- Hypocoercivity
- Optimal Scaling of Discrete Approximations to Langevin Diffusions
- Spectral methods for Langevin dynamics and associated error estimates
- Ordinary Differential Equations with Applications
- Stochastic Processes and Applications
- Hypocoercivity for linear kinetic equations conserving mass
- Jump Control of Probability Densities With Applications to Autonomous Vehicle Motion
- Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
- Perturbation Theory for Semi-Groups of Linear Operators
- Optimal Transport
This page was built for publication: Randomized Hamiltonian Monte Carlo as scaling limit of the bouncy particle sampler and dimension-free convergence rates
