Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
From MaRDI portal
Publication:5743237
DOI10.1111/rssb.12183zbMath1411.62030arXiv1412.7392OpenAlexW2222154095MaRDI QIDQ5743237
Publication date: 9 May 2019
Published in: Journal of the Royal Statistical Society Series B: Statistical Methodology (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1412.7392
Computational methods in Markov chains (60J22) Sampling theory, sample surveys (62D05) Discrete-time Markov processes on general state spaces (60J05) Convergence of probability measures (60B10) Applications of Brownian motions and diffusion theory (population genetics, absorption problems, etc.) (60J70)
Related Items (92)
Limit behavior of the invariant measure for Langevin dynamics ⋮ A Proximal Markov Chain Monte Carlo Method for Bayesian Inference in Imaging Inverse Problems: When Langevin Meets Moreau ⋮ 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 ⋮ Stochastic gradient Hamiltonian Monte Carlo for non-convex learning ⋮ Quantitative contraction rates for Markov chains on general state spaces ⋮ Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Nonconvex Stochastic Optimization: Nonasymptotic Performance Bounds and Momentum-Based Acceleration ⋮ Constrained ensemble Langevin Monte Carlo ⋮ Complexity of zigzag sampling algorithm for strongly log-concave distributions ⋮ Markov Chain Importance Sampling—A Highly Efficient Estimator for MCMC ⋮ Unnamed Item ⋮ Ergodicity of the infinite swapping algorithm at low temperature ⋮ Unnamed Item ⋮ Nonasymptotic bounds for sampling algorithms without log-concavity ⋮ On sampling from a log-concave density using kinetic Langevin diffusions ⋮ Exponential weights in multivariate regression and a low-rankness favoring prior ⋮ Bayesian Imaging Using Plug & Play Priors: When Langevin Meets Tweedie ⋮ On Irreversible Metropolis Sampling Related to Langevin Dynamics ⋮ Explicit contraction rates for a class of degenerate and infinite-dimensional diffusions ⋮ ALMOND: Adaptive Latent Modeling and Optimization via Neural Networks and Langevin Diffusion ⋮ PAC-Bayesian risk bounds for group-analysis sparse regression by exponential weighting ⋮ Birth–death dynamics for sampling: global convergence, approximations and their asymptotics ⋮ Functional inequalities for perturbed measures with applications to log-concave measures and to some Bayesian problems ⋮ Convergence rates of Gibbs measures with degenerate minimum ⋮ Global Optimization via Schrödinger–Föllmer Diffusion ⋮ Dimension Free Nonasymptotic Bounds on the Accuracy of High-Dimensional Laplace Approximation ⋮ Phase transitions for support recovery under local differential privacy ⋮ Convergence of Langevin-simulated annealing algorithms with multiplicative noise. II: Total variation ⋮ Optimising portfolio diversification and dimensionality ⋮ Unadjusted Langevin algorithm with multiplicative noise: total variation and Wasserstein bounds ⋮ Complexity results for MCMC derived from quantitative bounds ⋮ Gradient-Based Markov Chain Monte Carlo for Bayesian Inference With Non-differentiable Priors ⋮ Nonasymptotic estimates for stochastic gradient Langevin dynamics under local conditions in nonconvex optimization ⋮ Laplace priors and spatial inhomogeneity in Bayesian inverse problems ⋮ Unnamed Item ⋮ Swarm gradient dynamics for global optimization: the mean-field limit case ⋮ (Non)-penalized multilevel methods for non-uniformly log-concave distributions ⋮ Distributed event-triggered unadjusted Langevin algorithm for Bayesian learning ⋮ The Langevin Monte Carlo algorithm in the non-smooth log-concave case ⋮ Unbiased Estimation Using Underdamped Langevin Dynamics ⋮ Variance reduction for Markov chains with application to MCMC ⋮ Bridging the gap between constant step size stochastic gradient descent and Markov chains ⋮ Optimal scaling of random-walk Metropolis algorithms on general target distributions ⋮ Taming Neural Networks with TUSLA: Nonconvex Learning via Adaptive Stochastic Gradient Langevin Algorithms ⋮ A Random-Batch Monte Carlo Method for Many-Body Systems with Singular Kernels ⋮ Multi-index antithetic stochastic gradient algorithm ⋮ Unnamed Item ⋮ The forward-backward envelope for sampling with the overdamped Langevin algorithm ⋮ Finite-sample complexity of sequential Monte Carlo estimators ⋮ Ensemble preconditioning for Markov chain Monte Carlo simulation ⋮ On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case ⋮ Scaling Limit of the Stein Variational Gradient Descent: The Mean Field Regime ⋮ Maximum Likelihood Estimation of Regularization Parameters in High-Dimensional Inverse Problems: An Empirical Bayesian Approach. Part II: Theoretical Analysis ⋮ Quantitative Harris-type theorems for diffusions and McKean–Vlasov processes ⋮ Theoretical properties of quasi-stationary Monte Carlo methods ⋮ On the limitations of single-step drift and minorization in Markov chain convergence analysis ⋮ Mixing of Hamiltonian Monte Carlo on strongly log-concave distributions: continuous dynamics ⋮ Normalizing constants of log-concave densities ⋮ Unnamed Item ⋮ Unnamed Item ⋮ On Stochastic Gradient Langevin Dynamics with Dependent Data Streams: The Fully Nonconvex Case ⋮ Fourier transform MCMC, heavy-tailed distributions, and geometric ergodicity ⋮ The tamed unadjusted Langevin algorithm ⋮ User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient ⋮ Efficient Bayesian Computation by Proximal Markov Chain Monte Carlo: When Langevin Meets Moreau ⋮ Non-asymptotic guarantees for sampling by stochastic gradient descent ⋮ Is there an analog of Nesterov acceleration for gradient-based MCMC? ⋮ Approximation of heavy-tailed distributions via stable-driven SDEs ⋮ On the exponentially weighted aggregate with the Laplace prior ⋮ A duality formula and a particle Gibbs sampler for continuous time Feynman-Kac measures on path spaces ⋮ New particle representations for ergodic McKean-Vlasov SDEs ⋮ Unnamed Item ⋮ Efficient stochastic optimisation by unadjusted Langevin Monte Carlo. Application to maximum marginal likelihood and empirical Bayesian estimation ⋮ Multivariate approximations in Wasserstein distance by Stein's method and Bismut's formula ⋮ 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 ⋮ Variance Reduction for Dependent Sequences with Applications to Stochastic Gradient MCMC ⋮ Higher order Langevin Monte Carlo algorithm ⋮ Unadjusted Langevin algorithm for sampling a mixture of weakly smooth potentials ⋮ Maximum Entropy Methods for Texture Synthesis: Theory and Practice ⋮ Unnamed Item ⋮ Laplacian Smoothing Stochastic Gradient Markov Chain Monte Carlo ⋮ Stochastic Gradient Markov Chain Monte Carlo ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Ensemble Kalman Sampler: Mean-field Limit and Convergence Analysis ⋮ Data-free likelihood-informed dimension reduction of Bayesian inverse problems ⋮ Nonparametric Bayesian inference for reversible multidimensional diffusions ⋮ Hausdorff dimension, heavy tails, and generalization in neural networks* ⋮ Variance reduction for additive functionals of Markov chains via martingale representations
This page was built for publication: Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
