Quasi-symplectic Langevin Variational Autoencoder
This work addresses the problem of improving posterior estimation in VAEs for researchers and practitioners dealing with massive, high-dimensional datasets, representing an incremental advancement over existing MCMC-inspired methods like HVAE.
The authors tackled the challenge of building low-variance evidence lower bounds (ELBO) in variational autoencoders (VAEs) for large datasets by proposing a Langevin dynamic flow-based inference approach, which uses a quasi-symplectic integrator to avoid Hessian computation and shows theoretical and practical effectiveness compared to other gradient flow-based methods.
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 gradient flow-based methods.