Nicolo Cesa-Bianchi

Cooperation in networks of learning agents

Abstract

We study the power of cooperation in a network of communicating agents that solve a learning task. Agents use an underlying communication network to get information about the behavior of other agents. In the talk, we show the extent to which cooperation allows us to prove performance bounds that are strictly better than the known bounds for non-cooperating agents. Our results are formulated within the online learning setting, under both the full and partial feedback models.

About the speaker

Nicolò Cesa-Bianchi is professor of Computer Science at the University of Milan, where he is currently head of the Computer Science programs. He was President of the Association for Computational Learning and member of the steering committee of the EC-funded Network of Excellence PASCAL2. He served as action editor for the Machine Learning Journal, for IEEE Transactions on Information Theory, and for the Journal of Machine Learning Research. He is currently associate editor for the Journal of Information and Inference. He was program chair of the 13th Annual Conference on Computational Learning Theory and of the 13th International Conference on Algorithmic Learning Theory. He has held visiting positions at UC Santa Cruz, Graz Technical University, Ecole Normale Supérieure in Paris, Google, and Microsoft Research. His main research interest is the design and analysis of machine learning algorithms, with special emphasis on sequential learning problems. He is co-author of the monographs, Prediction, Learning, and Games, and Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems. He is recipient of a Google Research Award and of a Xerox Foundation UAC Award.