Monte Carlo Variational Auto-Encoders
This work provides a method to enhance VAE training for researchers and practitioners, though it is incremental as it builds on existing techniques like Annealed Importance Sampling.
The paper tackled the problem of improving variational approximations in variational auto-encoders (VAE) by addressing limitations of importance sampling in high dimensions, and it demonstrated performance gains on various applications.
Variational auto-encoders (VAE) are popular deep latent variable models which are trained by maximizing an Evidence Lower Bound (ELBO). To obtain tighter ELBO and hence better variational approximations, it has been proposed to use importance sampling to get a lower variance estimate of the evidence. However, importance sampling is known to perform poorly in high dimensions. While it has been suggested many times in the literature to use more sophisticated algorithms such as Annealed Importance Sampling (AIS) and its Sequential Importance Sampling (SIS) extensions, the potential benefits brought by these advanced techniques have never been realized for VAE: the AIS estimate cannot be easily differentiated, while SIS requires the specification of carefully chosen backward Markov kernels. In this paper, we address both issues and demonstrate the performance of the resulting Monte Carlo VAEs on a variety of applications.