GAME THEORY MEETS DEEP LEARNING

ABSTRACT 
Deep Learning has delivered significant advances in learning challenges across various data modalities including speech, image, and language, much of that progress being fueled by the success of gradient descent-based optimization methods in computing good solutions to non-convex optimization problems. From playing complex board games at super-human level to robustifying Deep Neural Net-based classifiers against adversarial attacks, training deep generative models, and training DNN-based models to interact with each other and with humans, many outstanding challenges in Deep Learning now lie at its interface with Game Theory. Since these applications involve multiple agents, the role of single-objective optimization is played by equilibrium computation. On this front, however, the Deep Learning toolkit has been less successful. Gradientdescent based methods struggle to converge, let alone to good solutions, and due to non-convexities, standard game-theoretic equilibrium concepts fail to exist. So how does one train DNNs to be strategic? And what is even the goal of the training? We shed light on these challenges through a combination of learning-theoretic, complexity-theoretic, game-theoretic and topological techniques, presenting obstacles and opportunities for Deep Learning and Game Theory going forward.

CONSTANTINOS COSTIS DASKALAKIS is the Avanessians Professor of Electrical Engineering and Computer Science at MIT. He works on Algorithms, Machine Learning, Game Theory, Economics, and Statistics. He has resolved long-standing open problems about the computational complexity of Nash equilibrium, and the mathematical structure and computational complexity of multi-item auctions. His current work focuses on multi-agent learning, high-dimensional statistics, learning from biased and dependent data, causal inference and econometrics. He has been honored with several top honors in his fields of research including the Nevanlinna Prize awarded, together with the Fields medal, by the International Mathematical Union for outstanding contributions to mathematical aspects of information sciences. Other prestigious honors include the ACM Doctoral Dissertation Award, the Kalai Prize from the Game Theory Society, the Simons Foundation Investigator Award, and the ACM Grace Murray Hopper Award. He is an ACM fellow, holds an honorary doctorate from the University of Patras, and was awarded the Golden Cross of the Order of the Redeemer by the Greek Presidency. He has served in the scientific and advisory board of the Simons Institute for the Theory of Computing (2018-2020), and as the head of the theory of computation group at MIT (2018-2022). He was recently appointed by the Greek PM to lead the AI Strategic Planning committee for Greece.

Please, note that registration is required and that access on the day of the event is guaranteed until the maximum capacity of the room is reached on a first-come first-served basis.

REGISTRATION FORM