[Theory] [Talks at TTIC] 3/18 TTIC Colloquium: Bruno Loureiro, École Normale Supérieure

[Brandie Jones]

*When:*        Monday, March 18th at *11:30am CT*


*Where:       *Talk will be given *live, in-person* at

                       TTIC, 6045 S. Kenwood Avenue

                       5th Floor, Room 530


*Virtually:*  via Panopto (livestream
<https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=1aa61fc0-f7ff-4627-ada9-b129012db0c3>
)


*Who: *         Bruno Loureiro, École Normale Supérieure

*Title:*          Learning features with two-layer neural networks, one
step at a time
*Abstract:  *Feature learning - or the capacity of neural networks to adapt
to the data during training - is often quoted as one of the fundamental
reasons behind their unreasonable effectiveness. Yet, making mathematical
sense of this seemingly clear intuition is still a largely open question.
In this talk, I will discuss a simple setting where we can precisely
characterise how features are learned by a two-layer neural network during
the very first few steps of training, and how these features are essential
for the network to efficiently generalise under limited availability of
data.

Based on the following works: https://arxiv.org/abs/2305.18270,
https://arxiv.org/abs/2402.04980

*Short Bio: *Bruno Loureiro is a CNRS researcher based at the Centre for
Data Science at the École Normale Supérieure in Paris working on the
crossroads between machine learning and statistical mechanics.

*Host: Nati Srebro <nati at ttic.edu>*

-- 
*Brandie Jones *
*Executive **Administrative Assistant*
Toyota Technological Institute
6045 S. Kenwood Avenue
Chicago, IL  60637
www.ttic.edu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20240306/33fce5e4/attachment.html>