Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore the intersection of machine learning and game theory in this Richard M. Karp Distinguished Lecture by MIT Professor Constantinos Daskalakis. Delve into the challenges of equilibrium computation in machine learning applications, including robustifying models against adversarial attacks, causal inference, training generative models, and learning in strategic environments. Examine why gradient descent-based optimization methods, successful in other areas of machine learning, often fail to find equilibria in game-theoretic scenarios. Gain insights into the obstacles and opportunities at the frontier of machine learning and game theory, and learn about the computational complexity of Nash equilibrium and multi-item auctions. Discover how this research impacts high-dimensional statistics and learning from biased, dependent, or strategic data.