(Non-) asymptotic properties of Stochastic Gradient Langevin Dynamics

zbMath1391.60178arXiv1501.00438MaRDI QIDQ2834489

Sebastian J. Vollmer, Konstantinos C. Zygalakis, Yee Whye Teh

Publication date: 22 November 2016

Full work available at URL: https://arxiv.org/abs/1501.00438

zbMATH Keywords

Markov chain Monte CarloLangevin dynamicsbig datafixed step size

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Bayesian inference (62F15) Monte Carlo methods (65C05) Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10) Applications of Brownian motions and diffusion theory (population genetics, absorption problems, etc.) (60J70)

Related Items (23)

An adaptive Hessian approximated stochastic gradient MCMC method ⋮ Multi-variance replica exchange SGMCMC for inverse and forward problems via Bayesian PINN ⋮ Unnamed Item ⋮ An adaptively weighted stochastic gradient MCMC algorithm for Monte Carlo simulation and global optimization ⋮ Nonasymptotic bounds for sampling algorithms without log-concavity ⋮ ALMOND: Adaptive Latent Modeling and Optimization via Neural Networks and Langevin Diffusion ⋮ Functional central limit theorem and strong law of large numbers for stochastic gradient Langevin dynamics ⋮ Improving sampling accuracy of stochastic gradient MCMC methods via non-uniform subsampling of gradients ⋮ Multi-index antithetic stochastic gradient algorithm ⋮ Unnamed Item ⋮ Efficient Bayesian Computation by Proximal Markov Chain Monte Carlo: When Langevin Meets Moreau ⋮ Markov chains in random environment with applications in queuing theory and machine learning ⋮ Measuring sample quality with diffusions ⋮ Multi-level Monte Carlo methods for the approximation of invariant measures of stochastic differential equations ⋮ Unnamed Item ⋮ Stochastic gradient Langevin dynamics with adaptive drifts ⋮ Efficient stochastic optimisation by unadjusted Langevin Monte Carlo. Application to maximum marginal likelihood and empirical Bayesian estimation ⋮ Geometry-informed irreversible perturbations for accelerated convergence of Langevin dynamics ⋮ Unnamed Item ⋮ Control variates for stochastic gradient MCMC ⋮ Laplacian Smoothing Stochastic Gradient Markov Chain Monte Carlo ⋮ Stochastic Gradient Markov Chain Monte Carlo ⋮ Unnamed Item

This page was built for publication: (Non-) asymptotic properties of Stochastic Gradient Langevin Dynamics