Home About Courses Apply Organizers and Sponsors

Deep Learning Theory Summer School at Princeton

July 27 - August 4, 2021

About

Welcome to the website for the Deep Learning Theory Summer School at Princeton 2021. The school will run remotely from July 27 to August 4, 2021 and is aimed at graduate students interested in the theory of deep learning. The primary goal is to showcase, through three main courses and a variety of short talks, a range of exciting developments. An important secondary goal is to connect young researchers and foster a closer community within theoretical machine learning. All graduate students with a technical background are to apply.

Courses

There will be three principle courses. Each course will consist of five one-hour lectures as well as pre-readings, problem sets, and TA sessions. These courses are:

  1. Modern Machine Learning and Deep Learning Through the Prism of Interpolation

    Instructor: Misha Belkin (UCSD Halicioglu)

    Pre-Readings:    RKHS and this article.

  2. Deep Learning: a Statistical Viewpoint

    Instructor: Andrea Montanari (Stanford)

    Pre-Readings:    Linear algebra at a somewhat advanced level (eigenvalues inequalities, perturbation theory etc), high dimensional probability (e.g. Chapters 1-6 in Vershynin), and classical statistical learning theory is welcome but not required (e.g. Ben-David and Shalev-Shwartz).

  3. Effective Theory of Deep Learning: Beyond the Infinite-Width Limit

    Instructors: Dan Roberts (MIT, Salesforce) and Sho Yaida (Facebook)

    Pre-Readings:    Chapters 0-2 in this book.

    Slides: Lecture 1, Lecture 2, Lecture 3, Lecture 4, Lecture 5

Overall Schedule

There will also be a number of individual talks from researchers in industry and academia, including Ben Adlam (Google), Leon Bottou (Facebook), Ethan Dyer (Google), Gintare Karolina Dziugaite (Element AI), Suriya Gunasekar (MSR), Guy Gur-Ari (Google), Daniel Park (Google), Jeffrey Pennington (Google), Marc'Aurelio Ranzato (Facebook), David Schwab (CUNY), Atlas Wang (Austin), Greg Yang (MSR).

Symposium Schedule

Lecture Video: Day 1, Day 2, Day 3, Day 4, Day 5, Day 6, Day 7

Apply

Graduate students in any technical discipline with a strong interest in theory are encouraged to apply, and prior experience in deep learning is not required. To submit an application for this summer school, please send a CV and brief statement of interest (one page or less) to dlschool@princeton.edu. Also, please arrange for one letter of recommendation to be sent on your behalf to the same address. Full consideration will be given to applications completed by March 31, 2021.

Organizers and Sponsors

This summer school is organized by Boris Hanin (Princeton ORFE ) with support from the Center for Statistics and Machine Learning (CSML). Funding was generously provided via the DataX program at Princeton.