HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Quasi-Symplectic Langevin Variational Autoencoder

Zihao Wang 1, * Hervé Delingette 1
* Corresponding author
Abstract : 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.
Document type :
Preprints, Working Papers, ...
Complete list of metadata

Contributor : Zihao Wang Connect in order to contact the contributor
Submitted on : Thursday, June 3, 2021 - 1:31:32 PM
Last modification on : Friday, February 4, 2022 - 3:25:21 AM


Files produced by the author(s)


  • HAL Id : hal-03024748, version 4


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



Record views


Files downloads