Learning variational autoencoders via MCMC speed measures

DOI10.1007/s11222-024-10481-xzbMath1545.6206MaRDI QIDQ6606966

Marcel Hirt, Petros Dellaportas, Vasileios Kreouzis

Publication date: 17 September 2024

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

zbMATH Keywords

adaptive MCMChierarchical modelsgenerative modelsHMCMALA

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Computational methods for problems pertaining to statistics (62-08)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Primal-dual subgradient methods for convex problems
• The No-U-Turn Sampler: Adaptively Setting Path Lengths in Hamiltonian Monte Carlo
• A general framework for the parametrization of hierarchical models
• Weak convergence and optimal scaling of random walk Metropolis algorithms
• On the geometric ergodicity of Hamiltonian Monte Carlo
• Probabilistic Principal Component Analysis
• Geometric numerical integration illustrated by the Störmer–Verlet method
• Particle Markov Chain Monte Carlo Methods
• Stochastic Normalizing Flows for Inverse Problems: A Markov Chains Viewpoint
• A Connection Between Score Matching and Denoising Autoencoders
• Geometric integrators and the Hamiltonian Monte Carlo method

This page was built for publication: Learning variational autoencoders via MCMC speed measures