Probability Functional Descent: A Unifying Perspective on GANs, Variational Inference, and Reinforcement Learning
Abstract
The goal of this paper is to provide a unifying view of a wide range of problems of interest in machine learning by framing them as the minimization of functionals defined on the space of probability measures. In particular, we show that generative adversarial networks, variational inference, and actor-critic methods in reinforcement learning can all be seen through the lens of our framework. We then discuss a generic optimization algorithm for our formulation, called probability functional descent (PFD), and show how this algorithm recovers existing methods developed independently in the settings mentioned earlier.
Cite
Text
Chu et al. "Probability Functional Descent: A Unifying Perspective on GANs, Variational Inference, and Reinforcement Learning." International Conference on Machine Learning, 2019.Markdown
[Chu et al. "Probability Functional Descent: A Unifying Perspective on GANs, Variational Inference, and Reinforcement Learning." International Conference on Machine Learning, 2019.](https://mlanthology.org/icml/2019/chu2019icml-probability/)BibTeX
@inproceedings{chu2019icml-probability,
title = {{Probability Functional Descent: A Unifying Perspective on GANs, Variational Inference, and Reinforcement Learning}},
author = {Chu, Casey and Blanchet, Jose and Glynn, Peter},
booktitle = {International Conference on Machine Learning},
year = {2019},
pages = {1213-1222},
volume = {97},
url = {https://mlanthology.org/icml/2019/chu2019icml-probability/}
}