Timezone: »

Random Utility Theory for Social Choice: Theory and Algorithms
Hossein Azari Soufiani · David C Parkes · Lirong Xia

Wed Dec 05 07:00 PM -- 12:00 AM (PST) @ Harrah’s Special Events Center 2nd Floor

Random utility theory models an agent's preferences on alternatives by drawing a real-valued score on each alternative (typically independently) from a parameterized distribution, and then ranking according to scores. A special case that has received significant attention is the Plackett-Luce model, for which fast inference methods for maximum likelihood estimators are available. This paper develops conditions on general, random utility models that enable fast inference within a Bayesian framework through MC-EM, providing unimodal log-likelihood functions. Results on both real-world and simulated data provide support for the scalability of the approach, despite its flexibility.

Author Information

Hossein Azari Soufiani (Harvard University)
David C Parkes (Harvard University)
Lirong Xia (RPI)

More from the Same Authors