High-order Langevin diffusion yields an accelerated MCMC algorithm

MaRDI QIDQ4998932zbMATH OpenFDO

Authors Wenlong Mou, Yi-An Ma, Martin J. Wainwright, Peter L. Bartlett, Michael Jordan

Publication date 9 July 2021

Full work available at URL https://arxiv.org/abs/1908.10859, https://jmlr.csail.mit.edu/papers/v22/20-576.html

zbMATH Keywords

Bayesian inferencediscretization of SDEsLangevin diffusionMarkov chain Monte Carlomixing time

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Higher order Langevin Monte Carlo algorithm
• Fast Langevin based algorithm for MCMC in high dimensions
• High-dimensional MCMC with a standard splitting scheme for the underdamped Langevin diffusion
• Analysis of Langevin Monte Carlo via convex optimization
• Log-concave sampling: Metropolis-Hastings algorithms are fast

Cites work

• A differential equation for modeling Nesterov's accelerated gradient method: theory and insights
• Adaptive thermostats for noisy gradient systems
• Convergence of Langevin MCMC in KL-divergence
• Coupling and convergence for Hamiltonian Monte Carlo
• Fast mixing of Metropolized Hamiltonian Monte Carlo: benefits of multi-step gradients
• High-dimensional Bayesian inference via the unadjusted Langevin algorithm
• scientific article; zbMATH DE number 1090880 (Why is no real title available?)
• scientific article; zbMATH DE number 1821102 (Why is no real title available?)
• Introductory lectures on convex optimization. A basic course.
• Log-concave sampling: Metropolis-Hastings algorithms are fast
• Long time accuracy of Lie-Trotter splitting methods for Langevin dynamics
• On sampling from a log-concave density using kinetic Langevin diffusions
• Optimal scaling for various Metropolis-Hastings algorithms.
• Optimal Transport
• Sampling can be faster than optimization
• Some effective methods for unconstrained optimization based on the solution of systems of ordinary differential equations
• The geometry of Markov diffusion generators
• Theoretical Guarantees for Approximate Sampling from Smooth and Log-Concave Densities
• User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient

Cited in

(14)

• Complexity of zigzag sampling algorithm for strongly log-concave distributions
• Accurate and robust splitting methods for the generalized Langevin equation with a positive prony series memory kernel
• Efficient Numerical Algorithms for the Generalized Langevin Equation
• scientific article; zbMATH DE number 7626720 (Why is no real title available?)
• scientific article; zbMATH DE number 7626757 (Why is no real title available?)
• On the Generalized Langevin Equation for Simulated Annealing
• Optimal friction matrix for underdamped Langevin sampling
• High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm
• Accelerated Bayesian imaging by relaxed proximal-point Langevin sampling
• Augmented projection Wasserstein distances: multi-dimensional projection with neural surface
• Convergence of simulated annealing using kinetic Langevin dynamics
• Appropriate state-dependent friction coefficient accelerates kinetic Langevin dynamics
• Hypocoercivity meets lifts
• A gentle introduction to gradient-based optimization and variational inequalities for machine learning

This page was built for publication: High-order Langevin diffusion yields an accelerated MCMC algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4998932)