The intersection of learning theory, game theory, and mechanism design is becoming increasingly relevant: (1) data input to machine learning algorithms is either owned or generated by self-interested parties, (2) machine learning is used to optimize economic systems (e.g., auction platforms) or to learn how to optimally act in strategic settings, (3) machine learning models used in critical systems are becoming prone to adversarial attacks, and (4) several machine learning approaches can be framed as finding the equilibrium of a game, as opposed to the minimizer of an objective function. The theoretical foundations of these problems lie at the intersection of learning theory, game theory, and mechanism design.

Already, online learning and game theory have played a key role in some landmark advances in machine learning. Online learning has provided some of the most successful optimization methods used in training large-scale deep neural networks. Game-theoretic modeling has enabled the design of generative adversarial networks (GANs) and inspired approaches for training deep neural network classifiers that are robust to adversarial attacks. Finally, min-max tree search and regret minimization algorithms are central in solving Go and Texas Hold’em. More broadly, the world is moving toward the coexistence of multiple AIs that learn from their interaction, which might be collaborative, strategic, or adversarial.

The objective of this program is to further advance the interaction between learning and games and rethink its mathematical foundations. The semester will study the foundations of (1) min-max optimization, (2) multi-agent reinforcement learning, (3) dynamical systems and learning, (4) behavioral game theory, (5) econometrics and learning, and (6) mechanism design and learning. Moreover, it will address practical challenges in application domains where these techniques seem most appropriate, such as (1) generative adversarial networks, (2) adversarial robustness, (3) learning with humans in the loop, (4) learning as a model of strategic behavior, and (5) interactions of multiple learners.

The semester aims to bring together members of different communities, including machine learning, economics, operations research, theoretical computer science, and social computing.

This program is partially supported by the Foundations of Data Science Institute. We gratefully acknowledge the support of the NSF through grant DMS-2023505.

All event participants are subject to the Code of Conduct described here.


Long-Term Participants (including Organizers)

Yu Bai (Salesforce Research)
Ioannis Mitliagkas (Mila - Quebec Artificial Intelligence Institute & University of Montreal)

Research Fellows

Visiting Graduate Students and Postdocs

Qinyi Chen (Massachusetts Institute of Technology)