Skill Rating for Generative Models

arXiv: Machine Learning, Volume abs/1808.04888, 2018.

Cited by: 0|Bibtex|Views142
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

We explore a new way to evaluate generative models using insights from evaluation of competitive games between human players. We show experimentally that tournaments between generators and discriminators provide an effective way to evaluate generative models. We introduce two methods for summarizing tournament outcomes: tournament win rat...More

Code:

Data:

Your rating :
0

 

Tags
Comments