Auto-Encoding Sequential Monte Carlo
This provides an incremental improvement for researchers working with deep generative models and structured probabilistic inference.
The paper tackles the problem of simultaneous model and proposal learning in structured probabilistic models by improving auto-encoding sequential Monte Carlo (AESMC), resulting in a faster, easier-to-implement, and scalable method.
We build on auto-encoding sequential Monte Carlo (AESMC): a method for model and proposal learning based on maximizing the lower bound to the log marginal likelihood in a broad family of structured probabilistic models. Our approach relies on the efficiency of sequential Monte Carlo (SMC) for performing inference in structured probabilistic models and the flexibility of deep neural networks to model complex conditional probability distributions. We develop additional theoretical insights and introduce a new training procedure which improves both model and proposal learning. We demonstrate that our approach provides a fast, easy-to-implement and scalable means for simultaneous model learning and proposal adaptation in deep generative models.