Exponential convergence of Langevin distributions and their discrete approximations
From MaRDI portal
Publication:1353419
DOI10.2307/3318418zbMath0870.60027OpenAlexW1983452151MaRDI QIDQ1353419
Richard L. Tweedie, Gareth O. Roberts
Publication date: 1 September 1997
Published in: Bernoulli (Search for Journal in Brave)
Full work available at URL: https://semanticscholar.org/paper/e86f414f860a1a70e16d9718c887f4eb59a51f62
Markov chain Monte Carlodiffusionsposterior distributionsgeometric ergodicitydiscrete approximationsMetropolis algorithmsirreducible Markov processesHastings algorithmsLangevin models
Diffusion processes (60J60) Random number generation in numerical analysis (65C10) Limit theorems in probability theory (60F99)
Related Items
ALMOND: Adaptive Latent Modeling and Optimization via Neural Networks and Langevin Diffusion, Bayesian Factor Analysis for Inference on Interactions, Bayes analysis of the generalized gamma AFT models for left truncated and right censored data, Birth–death dynamics for sampling: global convergence, approximations and their asymptotics, The Convergence of Markov Chain Monte Carlo Methods: From the Metropolis Method to Hamiltonian Monte Carlo, Advanced Multilevel Monte Carlo Methods, A Benchmark for the Bayesian Inversion of Coefficients in Partial Differential Equations, Accelerating adaptation in the adaptive Metropolis–Hastings random walk algorithm, Transport Monte Carlo: High-Accuracy Posterior Approximation via Random Transport, Gradient-based adaptive importance samplers, Robustifying models against adversarial attacks by Langevin dynamics, Image Denoising: The Deep Learning Revolution and Beyond—A Survey Paper, Flexible Bayesian inference for diffusion processesusing splines, Smoothing unadjusted Langevin algorithms for nonsmooth composite potential functions, Convergence of Position-Dependent MALA with Application to Conditional Simulation in GLMMs, Ergodicity of supercritical SDEs driven by \(\alpha \)-stable processes and heavy-tailed sampling, Simplest random walk for approximating Robin boundary value problems and ergodic limits of reflected diffusions, Gradient-Based Markov Chain Monte Carlo for Bayesian Inference With Non-differentiable Priors, Accelerating inference for stochastic kinetic models, Non-reversible guided Metropolis kernel, A large deviation principle for the empirical measures of Metropolis-Hastings chains, Energy-Based Models with Applications to Speech and Language Processing, (Non)-penalized multilevel methods for non-uniformly log-concave distributions, Decentralized Bayesian learning with Metropolis-adjusted Hamiltonian Monte Carlo, Distributed event-triggered unadjusted Langevin algorithm for Bayesian learning, A statistical approach to estimating adsorption-isotherm parameters in gradient-elution preparative liquid chromatography, Speed up Zig-Zag, On the accept-reject mechanism for Metropolis-Hastings algorithms, Markov chain stochastic DCA and applications in deep learning with PDEs regularization, The Split Gibbs Sampler Revisited: Improvements to Its Algorithmic Structure and Augmented Target Distribution, Self-Supervised Deep Learning for Image Reconstruction: A Langevin Monte Carlo Approach, CUQIpy: I. Computational uncertainty quantification for inverse problems in Python, Online MCMC Thinning with Kernelized Stein Discrepancy, A fresh Take on ‘Barker Dynamics’ for MCMC, Optimal scaling of MCMC beyond Metropolis, Improving sampling accuracy of stochastic gradient MCMC methods via non-uniform subsampling of gradients, Multilevel Delayed Acceptance MCMC, Hamiltonian-Assisted Metropolis Sampling, Convergence of unadjusted Hamiltonian Monte Carlo for mean-field models, Efficient Bayesian Computation for Low-Photon Imaging Problems, Efficient and generalizable tuning strategies for stochastic gradient MCMC, The forward-backward envelope for sampling with the overdamped Langevin algorithm, Chilled sampling for uncertainty quantification: a motivation from a meteorological inverse problem *, Ensemble-Based Gradient Inference for Particle Methods in Optimization and Sampling, Bayesian Trend Filtering via Proximal Markov Chain Monte Carlo, Optimal control for sampling the transition path process and estimating rates, Lévy Langevin Monte Carlo, Quantitative bounds of convergence for geometrically ergodic Markov chain in the Wasserstein distance with application to the Metropolis adjusted Langevin algorithm, Bayesian computation: a summary of the current state, and samples backwards and forwards, MCMC methods for functions: modifying old algorithms to make them faster, Spatial and spatio-temporal log-Gaussian Cox processes: extending the geostatistical paradigm, On parallelizable Markov chain Monte Carlo algorithms with waste-recycling, Calibrate, emulate, sample, Optimal scaling of MaLa for nonlinear regression., Optimal scaling of random walk Metropolis algorithms using Bayesian large-sample asymptotics, Markov chain Monte Carlo confidence intervals, ISALT: inference-based schemes adaptive to large time-stepping for locally Lipschitz ergodic systems, Partial mixing and Edgeworth expansion, Information-geometric Markov chain Monte Carlo methods using diffusions, Central limit theorem and self-normalized Cramér-type moderate deviation for Euler-Maruyama scheme, Oracle lower bounds for stochastic gradient sampling algorithms, Improved bounds for discretization of Langevin diffusions: near-optimal rates without convexity, Stochastic zeroth-order discretizations of Langevin diffusions for Bayesian inference, Variance reduction using nonreversible Langevin samplers, Weighted multilevel Langevin simulation of invariant measures, Dynamic polymers: invariant measures and ordering by noise, The Euler scheme for stochastic differential equations with discontinuous drift coefficient: a numerical study of the convergence rate, Constrained ensemble Langevin Monte Carlo, Sampling from a log-concave distribution with projected Langevin Monte Carlo, Markov chain Monte Carlo and irreversibility, Penalised t-walk MCMC, Ergodicity of the infinite swapping algorithm at low temperature, Variance bounding of delayed-acceptance kernels, Non-reversible Metropolis-Hastings, An adaptively weighted stochastic gradient MCMC algorithm for Monte Carlo simulation and global optimization, Scalable methods for Bayesian selective inference, Error estimates of the backward Euler-Maruyama method for multi-valued stochastic differential equations, Multiplicative random walk Metropolis-Hastings on the real line, Convergent stochastic expectation maximization algorithm with efficient sampling in high dimension. Application to deformable template model estimation, Ergodicity and exponential \(\beta\)-mixing bounds for multidimensional diffusions with jumps, On sampling from a log-concave density using kinetic Langevin diffusions, Computing ergodic limits for Langevin equations, Adaptive Euler-Maruyama method for SDEs with nonglobally Lipschitz drift, Optimal scaling of the MALA algorithm with irreversible proposals for Gaussian targets, Variance reduction for Markov chains with application to MCMC, Itô-SDE MCMC method for Bayesian characterization of errors associated with data limitations in stochastic expansion methods for uncertainty quantification, Metropolis-Hastings algorithms with acceptance ratios of nearly 1, Stability of partially implicit Langevin schemes and their MCMC variants, Langevin incremental mixture importance sampling, Parallel hierarchical sampling: a general-purpose interacting Markov chains Monte Carlo algorithm, Limit theorems for some adaptive MCMC algorithms with subgeometric kernels. II, Perturbation theory for Markov chains via Wasserstein distance, Strong convergence of an explicit numerical method for SDEs with nonglobally Lipschitz continuous coefficients, Multimodal, high-dimensional, model-based, Bayesian inverse problems with applications in biomechanics, On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case, Controlled sequential Monte Carlo, Wavelet-based priors accelerate maximum-a-posteriori optimization in Bayesian inverse problems, Optimal scaling for various Metropolis-Hastings algorithms., Variance bounding Markov chains, Simulating Coulomb and log-gases with hybrid Monte Carlo algorithms, Informed reversible jump algorithms, Theoretical properties of quasi-stationary Monte Carlo methods, From ODE to open Markov chains, via SDE: an application to models for infections in individuals and populations, Normalizing constants of log-concave densities, Self-healing umbrella sampling: convergence and efficiency, Irreducibility and geometric ergodicity of Hamiltonian Monte Carlo, Proposals which speed up function-space MCMC, Improving dynamical properties of metropolized discretizations of overdamped Langevin dynamics, An adaptive approach to Langevin MCMC, An Explicit Link between Gaussian Fields and Gaussian Markov Random Fields: The Stochastic Partial Differential Equation Approach, f-SAEM: a fast stochastic approximation of the EM algorithm for nonlinear mixed effects models, Divergence of the backward Euler method for ordinary stochastic differential equations, Asymptotic expansion formulas for functionals of \(\varepsilon\)-Markov processes with a mixing property, Subgeometric ergodicity of strong Markov processes, The tamed unadjusted Langevin algorithm, Diffusion maps tailored to arbitrary non-degenerate Itô processes, User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient, Bayesian density estimation from grouped continuous data, Hitting time and convergence rate bounds for symmetric Langevin diffusions, A review and comparison of age-period-cohort models for cancer incidence, Stochastic seismic waveform inversion using generative adversarial networks as a geological prior, Measuring sample quality with diffusions, Erratum to ``A comparison of generalized hybrid Monte Carlo methods with and without momentum flip, Non-asymptotic guarantees for sampling by stochastic gradient descent, Approximation of heavy-tailed distributions via stable-driven SDEs, Subgeometric rates of convergence of \(f\)-ergodic strong Markov processes, A comparison of generalized hybrid Monte Carlo methods with and without momentum flip, The Bayesian update: variational formulations and gradient flows, Iterative construction of Gaussian process surrogate models for Bayesian inference, Multi-level Monte Carlo methods for the approximation of invariant measures of stochastic differential equations, Efficient stochastic optimisation by unadjusted Langevin Monte Carlo. Application to maximum marginal likelihood and empirical Bayesian estimation, Particle-based energetic variational inference, A piecewise deterministic Monte Carlo method for diffusion bridges, Bayesian inference with subset simulation: strategies and improvements, Multivariate approximations in Wasserstein distance by Stein's method and Bismut's formula, Sampling from non-smooth distributions through Langevin diffusion, Non-stationary phase of the MALA algorithm, Geometric adaptive Monte Carlo in random environment, Spectral thresholding for the estimation of Markov chain transition operators, Randomized Hamiltonian Monte Carlo as scaling limit of the bouncy particle sampler and dimension-free convergence rates, High-dimensional Bayesian inference via the unadjusted Langevin algorithm, On the geometric ergodicity of Hamiltonian Monte Carlo, Higher order Langevin Monte Carlo algorithm, Hybrid Monte Carlo methods for sampling probability measures on submanifolds, Geometry-informed irreversible perturbations for accelerated convergence of Langevin dynamics, Control variates for stochastic gradient MCMC, Smoothed Langevin proposals in Metropolis-Hastings algorithms., Invariant measures for multidimensional fractional stochastic volatility models, Plateau proposal distributions for adaptive component-wise multiple-try metropolis, Automatic zig-zag sampling in practice, Bayesian learning via neural Schrödinger-Föllmer flows, Shape-constrained semiparametric additive stochastic volatility models, Mini-Batch Metropolis–Hastings With Reversible SGLD Proposal, An efficient proposal distribution for Metropolis-Hastings using a \(B\)-splines technique, Derivative-Free Bayesian Inversion Using Multiscale Dynamics, A Micro-Macro Markov Chain Monte Carlo Method for Molecular Dynamics using Reaction Coordinate Proposals, Prior normalization for certified likelihood-informed subspace detection of Bayesian inverse problems, Efficient derivative-free Bayesian inference for large-scale inverse problems, A Proximal Markov Chain Monte Carlo Method for Bayesian Inference in Imaging Inverse Problems: When Langevin Meets Moreau, Proximal Markov chain Monte Carlo algorithms, Convergence of tamed Euler schemes for a class of stochastic evolution equations, Stochastic Normalizing Flows for Inverse Problems: A Markov Chains Viewpoint, Noisy Monte Carlo: convergence of Markov chains with approximate transition kernels, Transport Map Accelerated Markov Chain Monte Carlo, Particle dual averaging: optimization of mean field neural network with global convergence rate analysis*, Multilevel Monte Carlo method for ergodic SDEs without contractivity, On the Flexibility of Metropolis-Hastings Acceptance Probabilities in Auxiliary Variable Proposal Generation, Markov Chain Importance Sampling—A Highly Efficient Estimator for MCMC, Unnamed Item, Numerical Methods for Stochastic Simulation: When Stochastic Integration Meets Geometric Numerical Integration, On the computational complexity of MCMC-based estimators in large samples, Stochastic modelling of urban structure, Approximate Bayesian Inference for Latent Gaussian models by using Integrated Nested Laplace Approximations, A gentle stochastic thermostat for molecular dynamics, Exponential Mean-Square Stability of Numerical Solutions to Stochastic Differential Equations, Geometric ergodicity of the bouncy particle sampler, Neural Parametric Fokker--Planck Equation, Efficient estimation of hydraulic conductivity heterogeneity with non-redundant measurement information, Ensemble Inference Methods for Models With Noisy and Expensive Likelihoods, Numerical approximations of stochastic differential equations with non-globally Lipschitz continuous coefficients, Dimension-Independent MCMC Sampling for Inverse Problems with Non-Gaussian Priors, Bayesian Imaging Using Plug & Play Priors: When Langevin Meets Tweedie, On Irreversible Metropolis Sampling Related to Langevin Dynamics, PAC-Bayesian risk bounds for group-analysis sparse regression by exponential weighting, Adaptive schemes for piecewise deterministic Monte Carlo algorithms, Bounding Stationary Averages of Polynomial Diffusions via Semidefinite Programming, Unnamed Item, Scalable Optimization-Based Sampling on Function Space, A Random-Batch Monte Carlo Method for Many-Body Systems with Singular Kernels, Coarse-Graining of Overdamped Langevin Dynamics via the Mori--Zwanzig Formalism, An adaptive version for the Metropolis adjusted Langevin algorithm with a truncated drift, Stochastic Gradient Descent in Continuous Time, Optimal tuning of the hybrid Monte Carlo algorithm, Unnamed Item, Stratification as a General Variance Reduction Method for Markov Chain Monte Carlo, Bayesian Inverse Problems with $l_1$ Priors: A Randomize-Then-Optimize Approach, Fluctuations and temperature effects in bose-einstein condensation, Scalable inference for space‐time Gaussian Cox processes, Error bounds for Metropolis-Hastings algorithms applied to perturbations of Gaussian measures in high dimensions, Continuous-time Random Walks for the Numerical Solution of Stochastic Differential Equations, An Adaptive Euler--Maruyama Scheme for Stochastic Differential Equations with Discontinuous Drift and its Convergence Analysis, Scaling Limit of the Stein Variational Gradient Descent: The Mean Field Regime, Analysis of Multiscale Integrators for Multiple Attractors and Irreversible Langevin Samplers, Langevin diffusions and the Metropolis-adjusted Langevin algorithm, MCMC METHODS FOR DIFFUSION BRIDGES, Accelerating Proximal Markov Chain Monte Carlo by Using an Explicit Stabilized Method, Maximum Likelihood Estimation of Regularization Parameters in High-Dimensional Inverse Problems: An Empirical Bayesian Approach. Part II: Theoretical Analysis, Pathwise accuracy and ergodicity of metropolized integrators for SDEs, Using Coupling Methods to Estimate Sample Quality of Stochastic Differential Equations, SPECTRWM: Spectral Random Walk Method for the Numerical Solution of Stochastic Partial Differential Equations, Langevin Dynamics With General Kinetic Energies, Unnamed Item, Unnamed Item, Observation-based correction of dynamical models using thermostats, Bayesian Spatio-Dynamic Modeling in Cell Motility Studies: Learning Nonlinear Taxic Fields Guiding the Immune Response, Random Batch Algorithms for Quantum Monte Carlo Simulations, Exact Simulation for Diffusion Bridges: An Adaptive Approach, An ergodic sampling scheme for constrained Hamiltonian systems with applications to molecular dynamics, Searching for efficient Markov chain Monte Carlo proposal kernels, Chain Graph Models and their Causal Interpretations, Markov-chain monte carlo: Some practical implications of theoretical results, Error analysis of the transport properties of Metropolized schemes, Adaptive Thermostats for Noisy Gradient Systems, Efficient Bayesian Computation by Proximal Markov Chain Monte Carlo: When Langevin Meets Moreau, Theoretical and numerical comparison of some sampling methods for molecular dynamics, Langevin type limiting processes for adaptive MCMC, Some Remarks on Preconditioning Molecular Dynamics, INLA or MCMC? A tutorial and comparative evaluation for spatial prediction in log-Gaussian Cox processes, Some new results on relative entropy production, time reversal, and optimal control of time-inhomogeneous diffusion processes, Adaptive Step Size Selection for Hessian-Based Manifold Langevin Samplers, Unnamed Item, Noisy Hamiltonian Monte Carlo for Doubly Intractable Distributions, A Bayesian Time-Varying Coefficient Model for Multitype Recurrent Events, Perfect Forward Simulation via Simulated Tempering, Geometric integrators and the Hamiltonian Monte Carlo method, Accelerated Dimension-Independent Adaptive Metropolis, Estimation of risk contributions with MCMC, Strong and weak divergence in finite time of Euler's method for stochastic differential equations with non-globally Lipschitz continuous coefficients, Variance Reduction for Dependent Sequences with Applications to Stochastic Gradient MCMC, Maximum Entropy Methods for Texture Synthesis: Theory and Practice, Metropolis Integration Schemes for Self-Adjoint Diffusions, Ergodicity for SDEs and approximations: locally Lipschitz vector fields and degenerate noise., Cut-off Phenomenon for Converging Processes in the Sense of α-Divergence Measures, Stochastic Gradient Markov Chain Monte Carlo, Unnamed Item, Ensemble Kalman Sampler: Mean-field Limit and Convergence Analysis, A Randomized Maximum A Posteriori Method for Posterior Sampling of High Dimensional Nonlinear Bayesian Inverse Problems, Joint estimation of Robin coefficient and domain boundary for the Poisson problem, Geometric Integration of Measure-Preserving Flows for Sampling, High-Dimensional Gaussian Sampling: A Review and a Unifying Approach Based on a Stochastic Proximal Point Algorithm, Stochastic Gradient MCMC for State Space Models
