Auto-Encoding Sequential Monte Carlo
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.
Cite
Text
Le et al. "Auto-Encoding Sequential Monte Carlo." International Conference on Learning Representations, 2018.Markdown
[Le et al. "Auto-Encoding Sequential Monte Carlo." International Conference on Learning Representations, 2018.](https://mlanthology.org/iclr/2018/le2018iclr-autoencoding/)BibTeX
@inproceedings{le2018iclr-autoencoding,
title = {{Auto-Encoding Sequential Monte Carlo}},
author = {Le, Tuan Anh and Igl, Maximilian and Rainforth, Tom and Jin, Tom and Wood, Frank},
booktitle = {International Conference on Learning Representations},
year = {2018},
url = {https://mlanthology.org/iclr/2018/le2018iclr-autoencoding/}
}