An entropic approach for Hamiltonian Monte Carlo: the idealized case
From MaRDI portal
Publication:6590457
Recommendations
- On the geometric ergodicity of Hamiltonian Monte Carlo
- Mixing of Hamiltonian Monte Carlo on strongly log-concave distributions: continuous dynamics
- Optimal convergence rate of Hamiltonian Monte Carlo for strongly logconcave distributions
- On L^2 convergence of the Hamiltonian Monte Carlo
- Optimal convergence rate of Hamiltonian Monte Carlo for strongly logconcave distributions
Cites work
- A note on Fisher information hypocoercive decay for the linear Boltzmann equation
- A note on Talagrand's transportation inequality and logarithmic Sobolev inequality
- A simple proof of the Poincaré inequality for a large class of probability measures
- Almost sure contraction for diffusions on \(\mathbb{R}^d\). Application to generalized Langevin diffusions
- An almost constant lower bound of the isoperimetric coefficient in the KLS conjecture
- Analysis and geometry of Markov diffusion operators
- Analysis of a nonreversible Markov chain sampler.
- Asymptotics of the spectral gap with applications to the theory of simulated annealing
- Bakry-Émery meet Villani
- Bourgain's slicing problem and KLS isoperimetry up to polylog
- Convergence of the kinetic annealing for general potentials
- Convergence of unadjusted Hamiltonian Monte Carlo for mean-field models
- Coupling and convergence for Hamiltonian Monte Carlo
- Couplings and quantitative contraction rates for Langevin dynamics
- Degenerate Fokker-Planck equations: Bismut formula, gradient estimate and Harnack inequality
- Detailed spectral study of processes that are less hesistent than others
- Diffusion and mixing in fluid flow
- Duality on gradient estimates and Wasserstein controls
- Entropic multipliers method for Langevin diffusion and weighted log Sobolev inequalities
- Equilibration Rate for the Linear Inhomogeneous Relaxation-Time Boltzmann Equation for Charged Particles
- Ergodicity for SDEs and approximations: locally Lipschitz vector fields and degenerate noise.
- Exact targeting of Gibbs distributions using velocity-jump processes
- Fast mixing of Metropolized Hamiltonian Monte Carlo: benefits of multi-step gradients
- Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality
- Generalized \(\Gamma\) calculus and application to interacting particles on a graph
- High-dimensional Bayesian inference via the unadjusted Langevin algorithm
- High-dimensional MCMC with a standard splitting scheme for the underdamped Langevin diffusion
- scientific article; zbMATH DE number 1975218 (Why is no real title available?)
- scientific article; zbMATH DE number 1851000 (Why is no real title available?)
- Hypocoercivity
- Hypocoercivity and exponential time decay for the linear inhomogeneous relaxation Boltzmann equation
- Hypocoercivity for linear kinetic equations conserving mass
- Hypocoercivity in metastable settings and kinetic simulated annealing
- Hypocoercivity in Phi-entropy for the linear relaxation Boltzmann equation on the torus
- Hypocoercivity of piecewise deterministic Markov process-Monte Carlo
- Hypoelliptic estimates and spectral theory for Fokker-Planck operators and Witten Laplacians
- Is there an analog of Nesterov acceleration for gradient-based MCMC?
- Isotropic hypoelliptic and trend to equilibrium for the Fokker-Planck equation with a high-degree potential
- Large and moderate deviations and exponential convergence for stochastic damping Hamiltonian systems.
- Log-concave sampling: Metropolis-Hastings algorithms are fast
- Log-Harnack inequality for stochastic differential equations in Hilbert spaces and its consequences
- Logarithmic Sobolev inequalities for finite Markov chains
- Long-time behaviour and propagation of chaos for mean field kinetic particles
- Mixing of Hamiltonian Monte Carlo on strongly log-concave distributions: continuous dynamics
- Mixing time guarantees for unadjusted Hamiltonian Monte Carlo
- Modified logarithmic Sobolev inequalities in discrete settings
- On explicit \(L^2\)-convergence rate estimate for piecewise deterministic Markov processes in MCMC algorithms
- On explicit L^2-convergence rate estimate for underdamped Langevin dynamics
- On sampling from a log-concave density using kinetic Langevin diffusions
- Optimal convergence rate of Hamiltonian Monte Carlo for strongly logconcave distributions
- Phi-entropy inequalities for diffusion semigroups
- Poincaré and logarithmic Sobolev inequalities by decomposition of the energy landscape
- Randomized Hamiltonian Monte Carlo
- Randomized Hamiltonian Monte Carlo as scaling limit of the bouncy particle sampler and dimension-free convergence rates
- Rate of convergence for ergodic continuous Markov processes: Lyapunov versus Poincaré
- Reflection coupling and Wasserstein contractivity without convexity
- Sampling can be faster than optimization
- Short and long time behavior of the Fokker-Planck equation in a confining potential and applications
- Simulated annealing via Sobolev inequalities
- Small eigenvalues of the low temperature linear relaxation Boltzmann equation with a confining potential
- Spectral gap for spherically symmetric \(\log\)-concave probability measures, and beyond
- The Andersen thermostat in molecular dynamics
- The Kannan-Lovász-Simonovits conjecture
- Trend to equilibrium and particle approximation for a weakly selfconsistent Vlasov-Fokker-Planck equation
- Uniform long-time and propagation of chaos estimates for mean field kinetic particles in non-convex landscapes
- Uniform Poincaré and logarithmic Sobolev inequalities for mean field particle systems
- Yet Another Look at Harris’ Ergodic Theorem for Markov Chains
Cited in
(11)- Convergence of unadjusted Hamiltonian Monte Carlo for mean-field models
- Randomized time Riemannian manifold Hamiltonian Monte Carlo
- Convergence of simulated annealing using kinetic Langevin dynamics
- \(L^2\)-Wasserstein contraction for Euler schemes of elliptic diffusions and interacting particle systems
- Unbiasing Hamiltonian Monte Carlo algorithms for a general Hamiltonian function
- L^2 geometric ergodicity for the kinetic Langevin process with non-equilibrium steady states
- The velocity jump Langevin process and its splitting scheme: long time convergence and numerical accuracy
- Transient subtraction: a control variate method for computing transport coefficients
- HMC and underdamped Langevin united in the unadjusted convex smooth case
- Reflection coupling for unadjusted generalized Hamiltonian Monte Carlo in the nonconvex stochastic gradient case
- Local convergence rates for Wasserstein gradient flows and McKean-Vlasov equations with multiple stationary solutions
This page was built for publication: An entropic approach for Hamiltonian Monte Carlo: the idealized case
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6590457)
