Mathematical foundations of AI

Date: October 6–10, 2025

Location: Harvard CMSA, Room G10, 20 Garden Street, Cambridge MA & via Zoom

Artificial intelligence (AI) has achieved unprecedented advances, yet our theoretical understanding lags significantly behind. This gap poses a significant obstacle to improving AI’s safety and reliability. Since the classical tools of learning theory have proven insufficient for understanding AI, researchers are now drawing insights from a vast array of fields—including functional analysis, probability theory, optimal transport, optimization, PDEs, information theory, geometry, statistics, electrical engineering, and ergodic theory. Those interdisciplinary efforts are gradually shedding light on the underlying principles governing modern AI. This workshop centers around these mathematical and interdisciplinary developments. It will feature a series of talks from people in various subfields. Open problem and small-group sessions will help foster new connections and new research avenues.

Registration required at website: https://cmsa.fas.harvard.edu/event/mathai/

Speakers

Jason Altschuler, University of Pennsylvania; Guy Bresler, MIT; Sinho Chewi, Yale University; Lenaic Chizat, EPFL; Nabarun Deb, University of Chicago; Edgar Dobriban, University of Pennsylvania; Ahmed El Alaoui, Cornell University; Zhou Fan, Yale University; Boris Hanin, Princeton University; Jason Klusowski, Princeton University; Tengyu Ma, Stanford University; Alexander Rakhlin, MIT; Yuting Wei, University of Pennsylvania; Tijana Zrnic, Stanford University

Organizer: Morgane Austern, Harvard Statistics