Stochastic gradient Langevin dynamics with adaptive drifts

DOI10.1080/00949655.2021.1958812MaRDI QIDQ3390482zbMATH OpenOpenAlexFDO

Authors Se-Hwan Kim, Qifan Song, Faming Liang

Publication date 24 March 2022

Published in Journal of Statistical Computation and Simulation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1080/00949655.2021.1958812

zbMATH Keywords

adaptive MCMCmomentumdeep neural networkstochastic gradient MCMCmini-batch data

Mathematics Subject Classification ID

Statistics (62-XX)

Cites work

• scientific article; zbMATH DE number 6781368 (Why is no real title available?)
• ADADELTA
• Adaptive subgradient methods for online learning and stochastic optimization
• Consistency and fluctuations for stochastic gradient Langevin dynamics
• Double-parallel Monte Carlo for Bayesian analysis of big data
• Ergodicity for SDEs and approximations: locally Lipschitz vector fields and degenerate noise.
• Exploration of the (non-)asymptotic bias and variance of stochastic gradient Langevin dynamics
• Optimization by simulated annealing
• Riemann manifold Langevin and Hamiltonian Monte Carlo methods. With discussion and authors' reply
• Scalable Bayes via barycenter in Wasserstein space
• Stochastic Approximation in Monte Carlo Computation
• Stochastic gradient Markov chain Monte Carlo
• The Bouncy Particle Sampler: A Non-Reversible Rejection-Free Markov Chain Monte Carlo Method
• The zig-zag process and super-efficient sampling for Bayesian analysis of big data
• User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient

Cited in

(8)

• Adaptive deep density approximation for Fokker-Planck equations
• A Stochastic Approximation-Langevinized Ensemble Kalman Filter Algorithm for State Space Models with Unknown Parameters
• Efficient and generalizable tuning strategies for stochastic gradient MCMC
• Hybrid deterministic-stochastic gradient Langevin dynamics for Bayesian learning
• Taming Neural Networks with TUSLA: Nonconvex Learning via Adaptive Stochastic Gradient Langevin Algorithms
• Self-Supervised Deep Learning for Image Reconstruction: A Langevin Monte Carlo Approach
• On Langevin Updating in Multilayer Perceptrons
• A stochastic Schumacher diffusion process: probability characteristics computation and statistical analysis

Describes a project that uses

Uses Software

• ADADELTA
• Adam
• RMSprop
• AdaGrad

This page was built for publication: Stochastic gradient Langevin dynamics with adaptive drifts

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3390482)