Auto-Encoding Sequential Monte Carlo
Tuan Anh Le, Maximilian Igl, Tom Rainforth, Tom Jin, Frank Wood
Abstract
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.
BibTeX
@inproceedings{
anh2018autoencoding,
title={Auto-Encoding Sequential Monte Carlo},
author={Tuan Anh Le and Maximilian Igl and Tom Rainforth and Tom Jin and Frank Wood},
booktitle={International Conference on Learning Representations},
year={2018},
url={https://openreview.net/forum?id=BJ8c3f-0b},
}