Abstract
Cooperation is often implicitly assumed when learning from other agents. Cooperation implies that the agent selecting the data, and the agent learning from the data, have the same goal, that the learner infer the intended hypothesis. Recent models in human and machine learning have demonstrated the possibility of cooperation. We seek foundational theoretical results for cooperative inference by Bayesian agents through sequential data. We develop novel approaches analyzing consistency, rate of convergence and stability of Sequential Cooperative Bayesian Inference (SCBI). Our analysis of the effectiveness, sample efficiency and robustness show that cooperation is not only possible in specific instances but theoretically well-founded in general. We discuss implications for human-human and human-machine cooperation.
Bio
Dr. Patrick Shafto is Professor of Mathematics and Computer Science at Rutgers University - Newark. Research in his lab focuses on theoretical and empirical foundations of cooperation and learning in humans and machines. He has received numerous honors and awards including an NSF CAREER award and his research has formed the basis for successful machine learning start-up companies. His research is supported by the NSF (EHR, CISE, SBE), DARPA, DoD, and the NIH.