Quasi-Symplectic Langevin Variational Autoencoder - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2021

Quasi-Symplectic Langevin Variational Autoencoder

Résumé

Variational autoencoder (VAE) is a very popular and well-investigated generative model vastly used in neural learning research. To leverage VAE in practical tasks dealing with a massive dataset of large dimensions it is required to deal with the difficulty of building low variance evidence lower bounds (ELBO). Markov Chain Monte Carlo (MCMC) is one of the effective approaches to tighten the ELBO for approximating the posterior distribution. Hamiltonian Variational Autoencoder (HVAE) is an effective MCMC inspired approach for constructing a the lowvariance ELBO which is also amenable to the reparameterization trick. In this work, we propose a Quasi-symplectic Langevin Variational autoencoder (LangevinVAE) by incorporating the gradients information in the inference process through Langevin dynamic. We shows the effectiveness of the proposed approach by toy and real world examples.
Fichier principal
Vignette du fichier
Langevin_VAE_Revision.pdf (364.54 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03024748 , version 1 (26-11-2020)
hal-03024748 , version 2 (23-03-2021)
hal-03024748 , version 3 (19-04-2021)
hal-03024748 , version 4 (03-06-2021)

Identifiants

  • HAL Id : hal-03024748 , version 3

Citer

Zihao Wang, Hervé Delingette. Quasi-Symplectic Langevin Variational Autoencoder. 2021. ⟨hal-03024748v3⟩
63 Consultations
449 Téléchargements

Partager

Gmail Facebook X LinkedIn More