Mixing of Hamiltonian Monte Carlo on strongly log-concave distributions: continuous dynamics

DOI10.1214/20-AAP1640zbMath1476.60112OpenAlexW3211106266WikidataQ114060533 ScholiaQ114060533MaRDI QIDQ2240875

Yanyan Li

Publication date: 4 November 2021

Published in: The Annals of Applied Probability (Search for Journal in Brave)

Full work available at URL: https://projecteuclid.org/journals/annals-of-applied-probability/volume-31/issue-5/Mixing-of-Hamiltonian-Monte-Carlo-on-strongly-log-concave-distributions/10.1214/20-AAP1640.full

zbMATH Keywords

Markov chain Monte Carlo (MCMC)momentumstrong convexityHamiltonian Monte Carlo (HMC)

Mathematics Subject Classification ID

Discrete-time Markov processes on general state spaces (60J05) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Numerical analysis or methods applied to Markov chains (65C40) Randomized algorithms (68W20)

Related Items

Oracle lower bounds for stochastic gradient sampling algorithms ⋮ Unnamed Item ⋮ Couplings for Andersen dynamics ⋮ Convergence of Position-Dependent MALA with Application to Conditional Simulation in GLMMs ⋮ Complexity results for MCMC derived from quantitative bounds ⋮ Convergence of unadjusted Hamiltonian Monte Carlo for mean-field models ⋮ Unnamed Item ⋮ 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 ⋮ Wasserstein-based methods for convergence complexity analysis of MCMC with applications

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Reflection couplings and contraction rates for diffusions
• Hanson-Wright inequality and sub-Gaussian concentration
• Gibbs sampling, exponential families and orthogonal polynomials
• Ricci curvature of Markov chains on metric spaces
• Honest exploration of intractable probability distributions via Markov chain Monte Carlo.
• Rapid mixing of geodesic walks on manifolds with positive curvature
• Randomized Hamiltonian Monte Carlo
• On comparison systems for ordinary differential equations
• On multivariate Gaussian tails
• Irreducibility and geometric ergodicity of Hamiltonian Monte Carlo
• On the geometric ergodicity of Hamiltonian Monte Carlo
• Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
• Optimal tuning of the hybrid Monte Carlo algorithm
• Simulated annealing in convex bodies and an \(O^{*}(n^{4}\)) volume algorithm
• Quantitative contraction rates for Markov chains on general state spaces
• Coupling and convergence for Hamiltonian Monte Carlo
• Complexity bounds for Markov chain Monte Carlo algorithms via diffusion limits
• The Markov chain Monte Carlo revolution
• Riemann Manifold Langevin and Hamiltonian Monte Carlo Methods
• Nonasymptotic mixing of the MALA algorithm
• Unbiased Hamiltonian Monte Carlo with couplings
• Convergence rate of Riemannian Hamiltonian Monte Carlo and faster polytope volume computation
• Stochastic localization + Stieltjes barrier = tight bound for log-Sobolev
• Theoretical and numerical comparison of some sampling methods for molecular dynamics
• Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
• Cost of the generalised hybrid Monte Carlo algorithm for free field theory