Paper Info
Title
Online Prediction with Selfish Experts.
Abstract
We consider the problem of binary prediction with expert advice in settings where experts have agency and seek to maximize their credibility. This paper makes three main contributions. First, it defines a model to reason formally about settings with selfish experts, and demonstrates that "incentive compatible" (IC) algorithms are closely related to the design of proper scoring rules. Second, we design IC algorithms with good performance guarantees for the absolute loss function. Third, we give a formal separation between the power of online prediction with selfish versus honest experts by proving lower bounds for both IC and non-IC algorithms. In particular, with selfish experts and the absolute loss function, there is no (randomized) algorithm for online prediction-IC or otherwise-with asymptotically vanishing regret.
Year
Venue
DocType
2017
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017)
Conference
Volume
ISSN
Citations 
30
1049-5258
0
PageRank 
References 
Authors
0.34
1
2
Name
Order
Citations
PageRank
Tim Roughgarden14177353.32
Okke Schrijvers221.07