convergence rateconvergence to equilibriumfinite-time transition probabilitygeometric ergodicityinvariant measuresMetropolis-adjusted Langevin algorithmMetropolis-Hastings algorithmspectral gapstochastic differential equationstransition probabilityweak accuracy
Ordinary differential equations and systems with randomness (34F05) Generation, random and stochastic difference and differential equations (37H10) Stochastic ordinary differential equations (aspects of stochastic analysis) (60H10) Applications of stochastic analysis (to PDEs, etc.) (60H30) Computational methods for stochastic equations (aspects of stochastic analysis) (60H35) Numerical solutions to stochastic differential and integral equations (65C30)
Abstract: The Metropolis-Adjusted Langevin Algorithm (MALA), originally introduced to sample exactly the invariant measure of certain stochastic differential equations (SDE) on infinitely long time intervals, can also be used to approximate pathwise the solution of these SDEs on finite time intervals. However, when applied to an SDE with a nonglobally Lipschitz drift coefficient, the algorithm may not have a spectral gap even when the SDE does. This paper reconciles MALA's lack of a spectral gap with its ergodicity to the invariant measure of the SDE and finite time accuracy. In particular, the paper shows that its convergence to equilibrium happens at exponential rate up to terms exponentially small in time-stepsize. This quantification relies on MALA's ability to exactly preserve the SDE's invariant measure and accurately represent the SDE's transition probability on finite time intervals.
Recommendations
- Non-stationary phase of the MALA algorithm
- Log-concave sampling: Metropolis-Hastings algorithms are fast
- Optimal scaling and diffusion limits for the Langevin algorithm in high dimensions
- Error bounds for Metropolis-Hastings algorithms applied to perturbations of Gaussian measures in high dimensions
- Nonasymptotic convergence analysis for the unadjusted Langevin algorithm
Cited in
(37)- On a generalization of the preconditioned Crank-Nicolson metropolis algorithm
- More on the long time stability of Feynman-Kac semigroups
- Oracle lower bounds for stochastic gradient sampling algorithms
- Improved bounds for discretization of Langevin diffusions: near-optimal rates without convexity
- On sampling from a log-concave density using kinetic Langevin diffusions
- On a perturbation theory and on strong convergence rates for stochastic ordinary and partial differential equations with nonglobally monotone coefficients
- Mixing of Hamiltonian Monte Carlo on strongly log-concave distributions: continuous dynamics
- The tamed unadjusted Langevin algorithm
- Non-stationary phase of the MALA algorithm
- Exponential moments for numerical approximations of stochastic partial differential equations
- On the geometric ergodicity of Hamiltonian Monte Carlo
- Numerical approximations of stochastic differential equations with non-globally Lipschitz continuous coefficients
- Dimension-Independent MCMC Sampling for Inverse Problems with Non-Gaussian Priors
- Reflection couplings and contraction rates for diffusions
- Exponential integrability properties of numerical approximation processes for nonlinear stochastic differential equations
- Scaling Limit of the Stein Variational Gradient Descent: The Mean Field Regime
- SPECTRWM: Spectral Random Walk Method for the Numerical Solution of Stochastic Partial Differential Equations
- Langevin dynamics with general kinetic energies
- Convergence of the likelihood ratio method for linear response of non-equilibrium stationary states
- Approximate spectral gaps for Markov chain mixing times in high dimensions
- Log-concave sampling: Metropolis-Hastings algorithms are fast
- Geometric integrators and the Hamiltonian Monte Carlo method
- Metropolis integration schemes for self-adjoint diffusions
- Improving dynamical properties of metropolized discretizations of overdamped Langevin dynamics
- Continuous-time random walks for the numerical solution of stochastic differential equations
- Partial differential equations and stochastic methods in molecular dynamics
- Error analysis of the transport properties of metropolized schemes
- Ensemble Kalman sampler: mean-field limit and convergence analysis
- Bayesian computation: a summary of the current state, and samples backwards and forwards
- Complexity results for MCMC derived from quantitative bounds
- Mixing of Metropolis-adjusted Markov chains via couplings: the high acceptance regime
- Convergence rates of Metropolis-Hastings algorithms
- Proximal oracles for optimization and sampling
- Sampling and estimation on manifolds using the Langevin diffusion
- Optimal scaling results for Moreau-Yosida Metropolis-adjusted Langevin algorithms
- Convergence and stability results for the particle system in the Stein gradient descent method
- Uniform minorization condition and convergence bounds for discretizations of kinetic Langevin dynamics
This page was built for publication: Nonasymptotic mixing of the MALA algorithm
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4907962)
