Theory of Deep Learning

Fall 2026 Thursdays 4:30–5:30 pm Sherrerd Hall 001 First meeting Sep 10 Boris Hanin (ORFE)

Informal seminar for PhD students with background in mathematics, physics, statistics, etc. The goal is to formulate core open problems at the intersection of theory and practice of deep learning.

For current Princeton affiliates only. Email bhanin 'at' princeton.edu if you're interested in attending.

Schedule

Introduction
Thu Sep 101 Overview what is a neural network; how it is used; the big questions of the course
Scaling laws
Thu Sep 172 Compactify the moduli space of neural networks → hyperparameter transfer opentransfer over the token horizon; the large-data regime
Thu Sep 243 High-dimensional limits of SGD openpower law exponents; optimizer design
Feature learning
Thu Oct 14 Near-linear windows: one gradient step; Bayesian posteriors openwhat gets learned, and when
Diffusion Models
Thu Oct 85 The score Hamiltonian opendiscrete time; schedules you would actually use
Thu Oct 156 Sampling ≲ score estimation (Chewi et al.) openupper vs. lower bounds
Thu Oct 22 no class — fall recess (Oct 17–25)
To be determined
Thu Oct 297 TBD
Thu Nov 58 TBD
Thu Nov 129 TBD
Thu Nov 19 TBD
Thu Nov 26 no class — Thanksgiving recess (Nov 25–29)
Thu Dec 310 TBD