Efficient and generalizable tuning strategies for stochastic gradient MCMC

DOI10.1007/s11222-023-10233-3zbMath1517.62011arXiv2105.13059MaRDI QIDQ6172924

Jeremie Coullon, Christopher Nemeth, L. F. South

Publication date: 20 July 2023

Published in: Statistics and Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2105.13059

zbMATH Keywords

Markov chain Monte Carlostochastic gradientStein discrepancyhyperparameter optimization

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08)

Cites Work

• Unnamed Item
• Robust adaptive Metropolis algorithm with coerced acceptance rate
• The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo
• Exponential convergence of Langevin distributions and their discrete approximations
• Weak convergence and optimal scaling of random walk Metropolis algorithms
• Optimal scaling and diffusion limits for the Langevin algorithm in high dimensions
• Control variates for stochastic gradient MCMC
• Adaptive Thermostats for Noisy Gradient Systems
• Stochastic gradient Langevin dynamics with adaptive drifts
• Optimal Scaling of Discrete Approximations to Langevin Diffusions
• Bandit Algorithms
• Introduction to Multi-Armed Bandits
• Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
• Stochastic Gradient Markov Chain Monte Carlo

This page was built for publication: Efficient and generalizable tuning strategies for stochastic gradient MCMC