Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Towards Principled Methods for Training Generative Adversarial Networks
Martin Arjovsky, Leon Bottou
Nov 04, 2016 (modified: Jan 12, 2017)ICLR 2017 conference submissionreaders: everyone
Abstract:The goal of this paper is not to introduce a single algorithm or method, but to make theoretical steps towards fully understanding the training dynamics of gen- erative adversarial networks. In order to substantiate our theoretical analysis, we perform targeted experiments to verify our assumptions, illustrate our claims, and quantify the phenomena. This paper is divided into three sections. The first sec- tion introduces the problem at hand. The second section is dedicated to studying and proving rigorously the problems including instability and saturation that arize when training generative adversarial networks. The third section examines a prac- tical and theoretically grounded direction towards solving these problems, while introducing new tools to study them.
TL;DR:We introduce a theory about generative adversarial networks and their issues.
Conflicts:nyu.edu, fb.com, umontreal.edu
Enter your feedback below and we'll get back to you as soon as possible.