"Incentive Compatible Regression Learning"

Speaker: Ariel Procaccia
Date: Thursday, 28 June 2007
Time: 11am
Place: Ross 201

Abstract:

We initiate the study of incentives in machine learning. We focus on a
game-theoretic regression learning setting where private information
is elicited from multiple agents, which are interested in different
distributions over the sample space; this conflict potentially gives
rise to untruthfulness on the part of the agents. We show that in a
specific setting and under mild assumptions, agents are motivated to
tell the truth. In a more general setting, we study the power and
limitations of mechanisms without payments. We finally establish that,
in the general setting, the VCG mechanism goes a long way in
guaranteeing truthfulness and efficiency.

Joint work with Ofer Dekel and Felix Fischer.