Couplings and quantitative contraction rates for Langevin dynamics

DOI10.1214/18-AOP1299zbMath1466.60160arXiv1703.01617OpenAlexW2592172378WikidataQ127546994 ScholiaQ127546994MaRDI QIDQ2327938

Andreas Eberle, Raphael Zimmer, Arnaud Guillin

Publication date: 8 October 2019

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

Full work available at URL: https://arxiv.org/abs/1703.01617

zbMATH Keywords

Lyapunov functions convergence to equilibrium Wasserstein distance hypocoercivity kinetic Fokker-Planck equation Langevin diffusion reflection coupling quantitative bounds stochastic Hamiltonian dynamics

Mathematics Subject Classification ID

Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Asymptotic behavior of solutions to PDEs (35B40) Diffusion processes (60J60) Fokker-Planck equations (35Q84)

Related Items

Uniform long-time and propagation of chaos estimates for mean field kinetic particles in non-convex landscapes, Limit behavior of the invariant measure for Langevin dynamics, Finding the jump rate for fastest decay in the Goldstein-Taylor model, Hypocoercivity with Schur complements, Oracle lower bounds for stochastic gradient sampling algorithms, Stochastic zeroth-order discretizations of Langevin diffusions for Bayesian inference, Stochastic gradient Hamiltonian Monte Carlo for non-convex learning, Random Batch Methods for Classical and Quantum Interacting Particle Systems and Statistical Samplings, Particle dual averaging: optimization of mean field neural network with global convergence rate analysis*, Multilevel Monte Carlo method for ergodic SDEs without contractivity, Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Nonconvex Stochastic Optimization: Nonasymptotic Performance Bounds and Momentum-Based Acceleration, Unnamed Item, Couplings for Andersen dynamics, Coupling and convergence for Hamiltonian Monte Carlo, Parameter and dimension dependence of convergence rates to stationarity for reflecting Brownian motions, On sampling from a log-concave density using kinetic Langevin diffusions, Coupling approach for exponential ergodicity of stochastic Hamiltonian systems with Lévy noises, On Irreversible Metropolis Sampling Related to Langevin Dynamics, On the Random Batch Method for Second Order Interacting Particle Systems, The inert drift atlas model, On explicit \(L^2\)-convergence rate estimate for underdamped Langevin dynamics, Exponential convergence in the Wasserstein metric \(W_1\) for one dimensional diffusions, Ergodicity and long-time behavior of the Random Batch Method for interacting particle systems, Time averages for kinetic Fokker-Planck equations, Convergence rates for nonequilibrium Langevin dynamics, On the Generalized Langevin Equation for Simulated Annealing, The method of stochastic characteristics for linear second-order hypoelliptic equations, Recent progress on limit theorems for large stochastic particle systems, Uniform-in-time propagation of chaos for kinetic mean field Langevin dynamics, Coupling by reflection for controlled diffusion processes: turnpike property and large time behavior of Hamilton-Jacobi-Bellman equations, Hypocoercivity Properties of Adaptive Langevin Dynamics, Almost sure contraction for diffusions on \(\mathbb{R}^d\). Application to generalized Langevin diffusions, Exponential ergodicity for damping Hamiltonian dynamics with state-dependent and non-local collisions, Taming Neural Networks with TUSLA: Nonconvex Learning via Adaptive Stochastic Gradient Langevin Algorithms, Convergence of unadjusted Hamiltonian Monte Carlo for mean-field models, Wasserstein contraction and Poincaré inequalities for elliptic diffusions with high diffusivity, Numerical computations of geometric ergodicity for stochastic dynamics, High-dimensional MCMC with a standard splitting scheme for the underdamped Langevin diffusion, Using Coupling Methods to Estimate Sample Quality of Stochastic Differential Equations, Well-posedness and long time behavior of singular Langevin stochastic differential equations, Unnamed Item, Unnamed Item, Unnamed Item, On Stochastic Gradient Langevin Dynamics with Dependent Data Streams: The Fully Nonconvex Case, Concentration inequalities for additive functionals: a martingale approach, Scaling limits for the generalized Langevin equation, The kinetic Fokker-Planck equation with mean field interaction, On the diffusive-mean field limit for weakly interacting diffusions exhibiting phase transitions, Gamma calculus beyond Villani and explicit convergence estimates for Langevin dynamics with singular potentials, Sticky couplings of multidimensional diffusions with different drifts, Two-scale coupling for preconditioned Hamiltonian Monte Carlo in infinite dimensions, Some new results on relative entropy production, time reversal, and optimal control of time-inhomogeneous diffusion processes, Efficient stochastic optimisation by unadjusted Langevin Monte Carlo. Application to maximum marginal likelihood and empirical Bayesian estimation, Geometric integrators and the Hamiltonian Monte Carlo method, Entropic multipliers method for Langevin diffusion and weighted log Sobolev inequalities, Convergence rates for the Vlasov-Fokker-Planck equation and uniform in time propagation of chaos in non convex cases, Entropic turnpike estimates for the kinetic Schrödinger problem, Robust Accelerated Gradient Methods for Smooth Strongly Convex Functions, Ensemble Kalman Sampler: Mean-field Limit and Convergence Analysis, Stochastic gradient descent and fast relaxation to thermodynamic equilibrium: A stochastic control approach, Mixing time guarantees for unadjusted Hamiltonian Monte Carlo, Convergence of a particle approximation for the quasi-stationary distribution of a diffusion process: Uniform estimates in a compact soft case

Cites Work