Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
From MaRDI portal
Convergence of probability measures (60B10) Discrete-time Markov processes on general state spaces (60J05) Computational methods in Markov chains (60J22) Applications of Brownian motions and diffusion theory (population genetics, absorption problems, etc.) (60J70) Sampling theory, sample surveys (62D05)
Abstract: Sampling from various kinds of distributions is an issue of paramount importance in statistics since it is often the key ingredient for constructing estimators, test procedures or confidence intervals. In many situations, the exact sampling from a given distribution is impossible or computationally expensive and, therefore, one needs to resort to approximate sampling strategies. However, there is no well-developed theory providing meaningful nonasymptotic guarantees for the approximate sampling procedures, especially in the high-dimensional problems. This paper makes some progress in this direction by considering the problem of sampling from a distribution having a smooth and log-concave density defined on (RR^p), for some integer (p>0). We establish nonasymptotic bounds for the error of approximating the target distribution by the one obtained by the Langevin Monte Carlo method and its variants. We illustrate the effectiveness of the established guarantees with various experiments. Underlying our analysis are insights from the theory of continuous-time diffusion processes, which may be of interest beyond the framework of log-concave densities considered in the present work.
Recommendations
- Log-Sobolev inequalities and sampling from log-concave distributions
- Sampling from log-concave distributions
- Nonasymptotic bounds for sampling algorithms without log-concavity
- Logarithmic sample bounds for sample average approximation with capacity- or budget-constraints
- Rapidly mixing chain and perfect sampler for logarithmic separable concave distributions on simplex
- Sample-optimal density estimation in nearly-linear time
Cited in
(only showing first 100 items - show all)- Log-Sobolev inequalities and sampling from log-concave distributions
- Sampling from log-concave distributions
- Explicit contraction rates for a class of degenerate and infinite-dimensional diffusions
- Ensemble preconditioning for Markov chain Monte Carlo simulation
- Normalizing constants of log-concave densities
- On the exponentially weighted aggregate with the Laplace prior
- Fourier transform MCMC, heavy-tailed distributions, and geometric ergodicity
- Is there an analog of Nesterov acceleration for gradient-based MCMC?
- Approximation of heavy-tailed distributions via stable-driven SDEs
- A duality formula and a particle Gibbs sampler for continuous time Feynman-Kac measures on path spaces
- Efficient stochastic optimisation by unadjusted Langevin Monte Carlo. Application to maximum marginal likelihood and empirical Bayesian estimation
- Sampling from non-smooth distributions through Langevin diffusion
- Randomized Hamiltonian Monte Carlo as scaling limit of the bouncy particle sampler and dimension-free convergence rates
- Unadjusted Langevin algorithm for sampling a mixture of weakly smooth potentials
- Nonparametric Bayesian inference for reversible multidimensional diffusions
- Variance reduction for additive functionals of Markov chains via martingale representations
- 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
- Constrained ensemble Langevin Monte Carlo
- Complexity of zigzag sampling algorithm for strongly log-concave distributions
- Ergodicity of the infinite swapping algorithm at low temperature
- On sampling from a log-concave density using kinetic Langevin diffusions
- Exponential weights in multivariate regression and a low-rankness favoring prior
- 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
- On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case
- 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
- The tamed unadjusted Langevin algorithm
- User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
- Non-asymptotic guarantees for sampling by stochastic gradient descent
- Multivariate approximations in Wasserstein distance by Stein's method and Bismut's formula
- High-dimensional Bayesian inference via the unadjusted Langevin algorithm
- Higher order Langevin Monte Carlo algorithm
- PAC-Bayesian risk bounds for group-analysis sparse regression by exponential weighting
- Quantitative contraction rates for Markov chains on general state spaces
- Nonasymptotic bounds for sampling algorithms without log-concavity
- Functional inequalities for perturbed measures with applications to log-concave measures and to some Bayesian problems
- Convergence rates of Gibbs measures with degenerate minimum
- Optimising portfolio diversification and dimensionality
- Nonasymptotic estimates for stochastic gradient Langevin dynamics under local conditions in nonconvex optimization
- Unifying presampling via concentration bounds
- Scaling Limit of the Stein Variational Gradient Descent: The Mean Field Regime
- Quantitative Harris-type theorems for diffusions and McKean-Vlasov processes
- Efficient Bayesian computation by proximal Markov chain Monte Carlo: when Langevin meets Moreau
- New particle representations for ergodic McKean-Vlasov SDEs
- On stationary-point hitting time and ergodicity of stochastic gradient Langevin dynamics
- Variance reduction for dependent sequences with applications to stochastic gradient MCMC
- High-order Langevin diffusion yields an accelerated MCMC algorithm
- Maximum entropy methods for texture synthesis: theory and practice
- Hausdorff dimension, heavy tails, and generalization in neural networks*
- 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
- scientific article; zbMATH DE number 7626754 (Why is no real title available?)
- scientific article; zbMATH DE number 7626757 (Why is no real title available?)
- Global convergence of stochastic gradient Hamiltonian Monte Carlo for nonconvex stochastic optimization: nonasymptotic performance bounds and momentum-based acceleration
- Markov Chain Importance Sampling—A Highly Efficient Estimator for MCMC
- Bayesian Imaging Using Plug & Play Priors: When Langevin Meets Tweedie
- On Irreversible Metropolis Sampling Related to Langevin Dynamics
- A Random-Batch Monte Carlo Method for Many-Body Systems with Singular Kernels
- Maximum likelihood estimation of regularization parameters in high-dimensional inverse problems: an empirical Bayesian approach. II: Theoretical analysis
- Asymptotic analysis via stochastic differential equations of gradient descent algorithms in statistical and computational paradigms
- scientific article; zbMATH DE number 7415079 (Why is no real title available?)
- Replica exchange for non-convex optimization
- On Stochastic Gradient Langevin Dynamics with Dependent Data Streams: The Fully Nonconvex Case
- Log-concave sampling: Metropolis-Hastings algorithms are fast
- Analysis of Langevin Monte Carlo via convex optimization
- Laplacian smoothing stochastic gradient Markov chain Monte Carlo
- Stochastic gradient Markov chain Monte Carlo
- Ensemble Kalman sampler: mean-field limit and convergence analysis
- Data-free likelihood-informed dimension reduction of Bayesian inverse problems
- Optimal convergence rate of Hamiltonian Monte Carlo for strongly logconcave distributions
- ALMOND: Adaptive Latent Modeling and Optimization via Neural Networks and Langevin Diffusion
- Birth–death dynamics for sampling: global convergence, approximations and their asymptotics
- 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
- 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
- Laplace priors and spatial inhomogeneity in Bayesian inverse problems
- 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
- Taming Neural Networks with TUSLA: Nonconvex Learning via Adaptive Stochastic Gradient Langevin Algorithms
- Multi-index antithetic stochastic gradient algorithm
- The forward-backward envelope for sampling with the overdamped Langevin algorithm
- Finite-sample complexity of sequential Monte Carlo estimators
- Contraction and convergence rates for discretized kinetic Langevin dynamics
- Hybrid unadjusted Langevin methods for high-dimensional latent variable models
- NF-ULA: normalizing flow-based unadjusted Langevin algorithm for imaging inverse problems
- Bayesian Robustness: A Nonasymptotic Viewpoint
- Swing contract pricing: with and without neural networks
This page was built for publication: Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5743237)
