Learning variational autoencoders via MCMC speed measures

Variational autoencoders (VAEs) are popular likelihood-based generative models which can be efficiently trained by maximising an evidence lower bound. There has been much progress in improving the expressiveness of the variational distribution to obtain tighter variational bounds and increased gener...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Statistics and computing Ročník 34; číslo 5
Hlavní autori: Hirt, Marcel, Kreouzis, Vasileios, Dellaportas, Petros
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York Springer US 01.10.2024
Springer Nature B.V
Predmet:
Artificial Intelligence
Computer Science
Lower bounds
Markov chains
Monte Carlo simulation
Optimization
Original Paper
Probability and Statistics in Computer Science
Statistical Theory and Methods
Statistics and Computing/Statistics Programs
Adaptive MCMC
MALA
Generative models
Hierarchical models
HMC
ISSN:0960-3174, 1573-1375
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Variational autoencoders (VAEs) are popular likelihood-based generative models which can be efficiently trained by maximising an evidence lower bound. There has been much progress in improving the expressiveness of the variational distribution to obtain tighter variational bounds and increased generative performance. Whilst previous work has leveraged Markov chain Monte Carlo methods for constructing variational densities, gradient-based methods for adapting the proposal distributions for deep latent variable models have received less attention. This work suggests an entropy-based adaptation for a short-run metropolis-adjusted Langevin or Hamiltonian Monte Carlo (HMC) chain while optimising a tighter variational bound to the log-evidence. Experiments show that this approach yields higher held-out log-likelihoods as well as improved generative metrics. Our implicit variational density can adapt to complicated posterior geometries of latent hierarchical representations arising in hierarchical VAEs.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0960-3174
1573-1375
DOI:10.1007/s11222-024-10481-x