Talk by Marcello Pelillo From Optima to Equilibria: Game-Theoretic Models of Pattern Analysis and Recognition

Title

From Optima to Equilibria: Game-Theoretic Models of Pattern Analysis and Recognition

 

Abstract

The development of game theory in the early 1940’s by John von Neumann was a reaction against the then dominant view that problems in economic theory should be formulated using standard optimization theory. Indeed, most real-world economic problems typically involve conflicting interactions among decision-making agents that cannot be adequately captured by a single (global) objective function, thereby requiring a more sophisticated treatment. Accordingly, the main point made by game theorists is to shift the emphasis from optimality criteria to equilibrium conditions. Because it provides an abstract, theoretically grounded framework to elegantly model complex scenarios, game theory has found a variety of applications not only in economics and, more generally, social sciences but also in different fields of engineering and information technologies. In this talk, after a short introduction to the basic concepts of game theory, I’ll provide an overview of the work I’ve done in the past few years aimed at reformulating a number of pattern recognition problems in terms of game-theoretic problems. These include, e.g., clustering, semi-supervised learning, graph matching, and contextual classification. Applications of these ideas to computer vision will be discussed. [I shall assume no pre-existing knowledge of game theory by the audience, thereby making the talk self-contained and understandable by a non-expert.]

 

Bio

Marcello Pelillo is a Professor of Computer Science at Ca’ Foscari University, Venice, where he leads the Computer Vision and Machine Learning Group. He has been the Director of the European Centre for Living Technology (ECLT) and has held visiting research positions at Yale University (USA), University College London (UK), McGill University (Canada), University of Vienna (Austria), York University (UK), NICTA (Australia), Wuhan University (China), Huazhong University of Science and Technology (Wuhan, China), South China University of Technology (Guangzhou, China). He is an external affiliate of the Computer Science Department at Drexel University (USA) and of the Italian Institute of Technology. His research interests are in the areas of computer vision, machine learning and pattern recognition where he has published more than 200 technical papers in refereed journals, handbooks, and conference proceedings. He has been General Chair for ICCV 2017, Program Chair for ICPR 2020, and he is regularly an Area Chair for the major conferences in his field. He is the Chief Editor of Frontiers in Computer Science – Computer Vision, and serves (or has served) on the Editorial Boards of several journals, including IEEE Transactions on Pattern Analysis and Machine Intelligence, Pattern Recognition, IET Computer Vision, Visual Intelligence, etc. He is also on the Advisory Board of Springer’s International Journal of Machine Learning and Cybernetics. Prof. Pelillo is Fellow of the IEEE, the IAPR, and the AAIA, and is an IEEE SMC Distinguished Lecturer.