Learning variational autoencoders via MCMC speed measures

DOI10.1007/S11222-024-10481-XzbMATH Open1545.6206MaRDI QIDQ6606966FDOQ6606966

Authors: Marcel Hirt, Vasileios Kreouzis, Petros Dellaportas 

Publication date: 17 September 2024

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

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

zbMATH Keywords

hierarchical modelsadaptive MCMCgenerative modelsHMCMALA

Mathematics Subject Classification ID

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

Cites Work

• The no-U-turn sampler: adaptively setting path lengths in Hamiltonian Monte Carlo
• Weak convergence and optimal scaling of random walk Metropolis algorithms
• A general framework for the parametrization of hierarchical models
• Particle Markov Chain Monte Carlo Methods
• Primal-dual subgradient methods for convex problems
• Probabilistic Principal Component Analysis
• A Connection Between Score Matching and Denoising Autoencoders
• Title not available (Why is that?)
• Geometric numerical integration illustrated by the Störmer–Verlet method
• On the geometric ergodicity of Hamiltonian Monte Carlo
• Log-concave sampling: Metropolis-Hastings algorithms are fast
• Geometric integrators and the Hamiltonian Monte Carlo method
• Title not available (Why is that?)
• Stochastic normalizing flows for inverse problems: a Markov chains viewpoint

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)