Robust Peer Prediction
Feb 05, 2014
from 01:10 PM to 03:00 PM
|Where||Engr. IV Bldg., Maxwell Room 57-124|
|Contact Name||Prof. Mihaela van der Schaar|
|Add event to calendar||
David C. Parkes
Many platforms need to promote users to invest effort in submitting accurate opinions; e.g., online product-rating platforms, votes on content curated on crowdsourcing platforms, and peer grading in massive open online courses (MOOCs). Frequently, it is important to align incentives towards informative inputs without access to gold standard answers. Peer prediction looks to address this problem by leveraging correlations between reports to make payments that promote effort and accuracy. However, classical solutions either require too much knowledge on the part of the mechanism designer or are otherwise fragile. In this talk, I will describe progress that we have made in the past few years on making peer prediction mechanisms more robust and better suited to practice. --Joint work with Jens Witkowski.
David C. Parkes is Harvard College Professor, George F. Colony Professor of Computer Science, and Area Dean for Computer Science at Harvard University, where he leads research at the interface between economics and computer science, with a focus on electronic commerce, artificial intelligence and machine learning. Parkes received his Ph.D. in Computer and Information Science from the University of Pennsylvania in 2001, and an M. Eng. in Engineering and Computing Science from Oxford University in 1995. Parkes has served as Program Chair of ACM EC'07 and AAMAS'08, and General Chair of ACM EC'10 and WINE 2013. Parkes is co- Program chair for HCOMP 14, and serves as the Chair of ACM SIGecom, Editor of Games and Economic Behavior, and on the editorial boards of Journal of Autonomous Agents and Multi-agent Systems, the ACM Transactions on Economics and Computation, and the INFORMS Journal of Computing.