Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models Without Sampling
Abstract
We present a new method for evaluating and training unnormalized density models. Our approach only requires access to the gradient of the unnormalized model’s log-density. We estimate the Stein discrepancy between the data density p(x) and the model density q(x) based on a vector function of the data. We parameterize this function with a neural network and fit its parameters to maximize this discrepancy. This yields a novel goodness-of-fit test which outperforms existing methods on high dimensional data. Furthermore, optimizing q(x) to minimize this discrepancy produces a novel method for training unnormalized models. This training method can fit large unnormalized models faster than existing approaches. The ability to both learn and compare models is a unique feature of the proposed method.
Cite
Text
Grathwohl et al. "Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models Without Sampling." International Conference on Machine Learning, 2020.Markdown
[Grathwohl et al. "Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models Without Sampling." International Conference on Machine Learning, 2020.](https://mlanthology.org/icml/2020/grathwohl2020icml-learning/)BibTeX
@inproceedings{grathwohl2020icml-learning,
title = {{Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models Without Sampling}},
author = {Grathwohl, Will and Wang, Kuan-Chieh and Jacobsen, Joern-Henrik and Duvenaud, David and Zemel, Richard},
booktitle = {International Conference on Machine Learning},
year = {2020},
pages = {3732-3747},
volume = {119},
url = {https://mlanthology.org/icml/2020/grathwohl2020icml-learning/}
}