Probability Functional Descent: A Unifying Perspective on GANs, Variational Inference, and Reinforcement Learning

This paper provides 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 method...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-05
Main Authors: Chu, Casey, Blanchet, Jose, Glynn, Peter
Format: Article
Language:English
Subjects:
Algorithms
Descent
Machine learning
Probabilistic inference
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper provides 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.
ISSN:2331-8422