Eliciting Expert Information without Verification

A central question of crowd-sourcing is how to elicit expertise from agents. This is even more difficult when answers cannot be directly verified. A key challenge holding back this field is that sophisticated agents may strategically withhold effort or information when they believe their payoff will be based upon comparison with other agents whose reports will likely omit this information due to lack of effort or expertise.

This talk will argue that information theory provides the "right way" to think about these problem. It will illustrate how information theoretic properties can directly translate into improved crowd-sourcing mechanisms. Additionally, I will show a novel connection between the mechanism design and learning from noisy data, a classic machine learning problem.

Finally, I will survey some of my work, in particular, on social networks including complex cascades, consensus/polarization, and understanding social network structure.

Grant Schoenebeck is an assistant professor at the University of Michigan in the Computer Science and Engineering division. His work spans diverse areas in theoretical computer science but has recently focused on applying ideas from theoretical computer science to the study of social networks and mechanism design for information elicitation. His research is supported by the NSF, Facebook, and Google including an NSF CAREER award. Before coming to the University of Michigan in 2012, he was a Postdoctoral Research Fellow at Princeton. Grant received his PhD at UC Berkeley, studied theology at Oxford University, and received his BA in mathematics and computer science from Harvard.