Optimal convergence rate of Hamiltonian Monte Carlo for strongly logconcave distributions

DOI10.4086/TOC.2022.V018A009MaRDI QIDQ5077151zbMATH OpenOpenAlexFDO

Authors Zongchen Chen, Santosh S. Vempala

Publication date 18 May 2022

Published in Theory of Computing (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/1905.02313

zbMATH Keywords

Hamiltonian Monte Carlologconcave distributionsamplingspectral gapstrong convexity

Mathematics Subject Classification ID

Discrete-time Markov processes on general state spaces (60J05) Continuous-time Markov processes on general state spaces (60J25) Theory of computing (68Qxx) Randomized algorithms (68W20)

Recommendations

• Optimal convergence rate of Hamiltonian Monte Carlo for strongly logconcave distributions
• Mixing of Hamiltonian Monte Carlo on strongly log-concave distributions: continuous dynamics
• On \(L^\mathfrak{q}\) convergence of the Hamiltonian Monte Carlo
• On L^2 convergence of the Hamiltonian Monte Carlo
• Log-concave sampling: Metropolis-Hastings algorithms are fast

Cited in

(14)

• Randomized Hamiltonian Monte Carlo as scaling limit of the bouncy particle sampler and dimension-free convergence rates
• Mixing time guarantees for unadjusted Hamiltonian Monte Carlo
• Couplings for Andersen dynamics
• On Irreversible Metropolis Sampling Related to Langevin Dynamics
• Optimal convergence rate of Hamiltonian Monte Carlo for strongly logconcave distributions
• Convergence of unadjusted Hamiltonian Monte Carlo for mean-field models
• On the dissipation of ideal Hamiltonian Monte Carlo sampler
• An entropic approach for Hamiltonian Monte Carlo: the idealized case
• Rapid convergence of the unadjusted Langevin algorithm: isoperimetry suffices
• Convergence in total variation for the kinetic Langevin algorithm
• Randomized transport plans via hierarchical fully probabilistic design
• Bayesian Federated Learning with Hamiltonian Monte Carlo: Algorithm and Theory
• Unadjusted Hamiltonian MCMC with stratified Monte Carlo time integration
• Multimodal sampling via Schrödinger-Föllmer samplers with temperatures

This page was built for publication: Optimal convergence rate of Hamiltonian Monte Carlo for strongly logconcave distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5077151)