QLS Lecture - Tuesday 9 February at 15:00 (CET)

[QLS]

Dear All,

on Tuesday, 9 February2021 at 15:00 CET, Sebastian Goldt,SISSA, will 
give a lecturetitled:

"The impact of data structure on learning in two-layer neural networks" 
(part 1)

Abstract: Understanding the impact of data structure on learning in 
neural networksremains a key challenge for the theory of neural networks.

In these two lectures, we will discuss how to go beyond the simple 
i.i.d. modelling paradigm in the teacher-student setupby studying neural 
networks trained on data drawn from structured generative models.

Our discussion will center around two results:

(1) We give rigorous conditions under which a class of generative models 
shares key statistical properties with an appropriatelychosen Gaussian 
feature model.

(2) We use this Gaussianequivalence to analyse the dynamics of two-layer 
neural networkstrained using one-pass stochastic gradient descent on 
data drawn from a largeclass of generators.

I will try to make these lectures self-contained.

They will be mostly based on the following two papers:

[1] Goldt, S., Mézard, M., Krzakala, F. and Zdeborová, L., 2020.
      Modeling the Influence of Data Structure on Learning in Neural 
Networks: The Hidden Manifold Model. /Physical Review X/, /10/(4), p.041044.

https://arxiv.org/abs/1909.11500 <https://arxiv.org/abs/1909.11500>

[2] Goldt, S., Reeves, G., Loureiro, B., Mézard, M., Krzakala, F. and 
Zdeborová, L., 2020.
      The Gaussian equivalence of generative models for learning with 
two-layer neural networks.
/     under review; https://arXiv.org/abs/2006.14709 
<https://arxiv.org/abs/2006.14709>/

http://indico.ictp.it/event/9563/

Zoom Meeting ID to attend the online seminar: 475-819-702

Join Zoom Meeting: https://zoom.us/j/475819702

 
<https://zoom.us/j/475819702

>

If you haven't registered for previous QLS webinars, please contact 
qls at ictp.it <mailto:qls at ictp.it> to obtain the PASSWORD for this zoom 
meeting.

Kind regards,
Barbara Valassi for QLS Section