Princeton Machine Learning Theory Summer School

About

Princeton University Shield

Welcome to the website for the Princeton Machine Learning Theory Summer School. The school will run in person August 6 - August 15, 2024 at Princeton and is aimed at PhD students interested in machine learning theory. The primary goal is to showcase, through four main courses, a range of exciting recent developments in the subject. The primary focus this year is on theoretical advances in deep learning. An important secondary goal is to connect young researchers and foster community within theoretical machine learning.

Courses & Schedule

Colorful Artistic Interpretation of a Neural Network as a Spherical Web of Connections

Principle courses, each consisting of four to five hours of lecture, are:

  1. Statistical physics for machine learning
    Instructor: Bruno Lourerio (ENS Paris)
  2. Acceleration and hedging in optimization Instructor: Jason Altschuler (UPenn/Wharton)
  3. Title TBD
    Instructors: Lenka Zdeborova and Florent Krzakala (EPFL)
  4. The fundamentals of interactive decision-making
    Instructor: Sasha Rakhlin (MIT)
  5. Title TBD
    Instructor: Morgane Austern (Harvard)
  6. Dense Associative Memory and Transformers
    Instructor: Dima Krotov (IBM/MIT)

Here's the schedule

schedule

 

Apply

Mathematics on a Chalk Board

PhD students in any technical discipline with a strong interest in theory are encouraged to apply. Accepted participants will be given free accommodation (double occupancy) in Princeton and will be eligible for a travel reimbursement of up to $500 (accepted students are encouraged to seek travel reimbursement from their advisor, department, school etc, however, to increase the number of students that can participate). Applications can be submitted here are due March 1, 2024 and require a CV, a letter of recommendation and a statement of purpose.

Organizers & Sponsors

This summer school is organized by Boris Hanin (Princeton ORFE). Support was provided by the NSF via NSF CAREER Grant DMS-2143754, the Department of Operations Research and Financial Engineering (ORFE) at Princeton, the Princeton School of Engineering and Applied Sciences (SEAS), the Program on Applied and Computational Mathematics (PACM) at Princeton, the Princeton Center for Theoretical Sciences (PCTS), and Princeton Language + Intelligence (PLI).