Quasi-Symplectic Langevin Variational Autoencoder - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year : 2021

Quasi-Symplectic Langevin Variational Autoencoder


Variational autoencoder (VAE) is a very popular and well-investigated generative model 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 an effective approach to tighten the ELBO for approximating the posterior distribution and Hamiltonian Variational Autoencoder (HVAE) is an effective MCMC inspired approach for constructing a low-variance ELBO that is amenable to the reparameterization trick. The HVAE adapted the Hamiltonian dynamic flow into variational inference that significantly improves the performance of the posterior estimation. We propose in this work a Langevin dynamic flow-based inference approach by incorporating the gradients information in the inference process through the Langevin dynamic which is a kind of MCMC based method similar to HVAE. Specifically, we employ a quasi-symplectic integrator to cope with the prohibit problem of the Hessian computing in naive Langevin flow. We show the theoretical and practical effectiveness of the proposed framework with other methods, which reaches the best negative log-likelihood on the benchmark dataset. The Langevin-VAE is used for modeling a clinical medical image dataset.
Fichier principal
Vignette du fichier
V2_Langevin_VAE_Revision__Copy_.pdf (610.52 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and 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)


  • HAL Id : hal-03024748 , version 4


Zihao Wang, Hervé Delingette. Quasi-Symplectic Langevin Variational Autoencoder. 2021. ⟨hal-03024748v4⟩
58 View
429 Download


Gmail Facebook X LinkedIn More