Theory of Modern AI: Learnability of Complex Objects
October 30, 2026 (1pm, GHC 8102 - part of the Theory Seminar series)

As machine learning and AI systems become increasingly pervasive and are deployed in high-stakes domains, developing theoretical foundations to understand and analyze their behavior has become more challenging, yet more pressing than ever before. Modern AI systems learn sophisticated structures that far exceed the analytical reach of classical frameworks in learning theory, theory of computing, and game theory, and increasingly operate in environments where learning occurs in the presence of other learners.

In this talk, I will present new directions for obtaining principled guarantees for increasingly complex AI systems. I will discuss general learnability guarantees for rich structured objects based on dual function classes and show how they apply to a broad range of settings, including using machine learning for algorithm design and automating hyperparameter tuning for machine learning itself. Finally, I will highlight emerging challenges for learning in the presence of other learners, spanning both cooperative settings and competitive strategic interactions.