Offline Contextual Bandits with High Probability Fairness Guarantees

Blossom Metevier
Blossom Metevier
Stephen Giguere
Stephen Giguere
Sarah Brockman
Sarah Brockman
Yuriy Brun
Yuriy Brun

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), pp. 14893-14904, 2019.

Cited by: 2|Bibtex|Views47
EI
Other Links: academic.microsoft.com|dblp.uni-trier.de
Keywords:

Abstract:

We present RobinHood, an offline contextual bandit algorithm designed to satisfy a broad family of fairness constraints. Our algorithm accepts multiple fairness definitions and allows users to construct their own unique fairness definitions for the problem at hand. We provide a theoretical analysis of RobinHood, which includes a proof tha...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments