Learning variational autoencoders via MCMC speed measures

DOI10.1007/S11222-024-10481-XMaRDI QIDQ6606966zbMATH OpenFDO

Authors Marcel Hirt, Vasileios Kreouzis, Petros Dellaportas

Publication date 17 September 2024

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

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1007/S11222-024-10481-X

zbMATH Keywords

adaptive MCMCgenerative modelshierarchical modelsHMCMALA

Mathematics Subject Classification ID

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

Recommendations

• Deep variational inference
• Improving latent variable descriptiveness by modelling rather than ad-hoc factors
• Variational Hamiltonian Monte Carlo via score matching
• \(\pi\) VAE: a stochastic process prior for Bayesian deep learning with MCMC
• Asymptotically exact inference in differentiable generative models

Cites work

• A Connection Between Score Matching and Denoising Autoencoders
• A general framework for the parametrization of hierarchical models
• Geometric integrators and the Hamiltonian Monte Carlo method
• Geometric numerical integration illustrated by the Störmer–Verlet method
• scientific article; zbMATH DE number 6982332 (Why is no real title available?)
• scientific article; zbMATH DE number 2152346 (Why is no real title available?)
• Log-concave sampling: Metropolis-Hastings algorithms are fast
• On the geometric ergodicity of Hamiltonian Monte Carlo
• Particle Markov Chain Monte Carlo Methods
• Primal-dual subgradient methods for convex problems
• Probabilistic Principal Component Analysis
• Stochastic normalizing flows for inverse problems: a Markov chains viewpoint
• The no-U-turn sampler: adaptively setting path lengths in Hamiltonian Monte Carlo
• Weak convergence and optimal scaling of random walk Metropolis algorithms

Cited in

(1)

• A moment-matching metric for latent variable generative models

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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6606966)