QLS Seminar being rescheduled - New date and time will follow ASAP - "Statistical physics of deep learning: Optimal learning of a multi-layer perceptron near interpolation" by Jean Barbier

[Quantitative Life Sciences]

Dear All,

As the seminar clashes with the In Memoriam gathering in honour of Karim 
Aoudia, it is being rescheduled.
The new date and time will be communicated ASAP.
Kind regards,
Erica


Erica Sarnataro
Group Secretary
Quantitative Life Sciences
The Abdus Salam International Centre for Theoretical Physics (ICTP)
Trieste,  Italy
Tel. +39-040-22404623 (NEW PHONE NUMBER)
www.ictp.it/research/qls.aspx
e-mail:qls at ictp.it 



-------- Forwarded Message --------
Subject: 	QLS Seminar - TOMORROW, 5 November at 11h00 "Statistical 
physics of deep learning: Optimal learning of a multi-layer perceptron 
near interpolation" by Jean Barbier
Date: 	Tue, 4 Nov 2025 11:48:12 +0100
From: 	Quantitative Life Sciences <qls at ictp.it>
To: 	Quantitative Life Sciences <qls at ictp.it>, science-ts at lists.ictp.it



Dear All,

  Jean Barbier(QLS and Mathematics Sections, ICTP) will give a seminar 
titled:

*"Statistical physics of deep learning: Optimal learning of a 
multi-layer perceptron near interpolation"

*Abstract:
For three decades, statistical physics has framed neural-network 
analysis, but its reach to expressive, feature-learning deep models was 
unclear. We answer yes by studying supervised learning in fully 
connected multi-layer nets whose hidden layers scale with input 
dimension—favoring feature learning over ultra-wide kernels while 
remaining more expressive than narrow or fixed-weight models—in the 
challenging interpolation regime where parameters and data are 
comparable. Using a matched teacher–student setup, we characterize 
fundamental performance limits and the sufficient statistics learned as 
data grows. The analysis uncovers rich phenomenology with multiple 
learning transitions: with enough data, optimal performance requires 
“specialization” of the student to the target, yet practical training 
can be trapped in sub-optimal solutions. Specialization is 
inhomogeneous—spreading from shallow to deep layers and unevenly across 
neurons—and deeper targets are intrinsically harder. Though derived in a 
Bayesian-optimal setting, the insights on nonlinearity, depth, and 
finite (proportional) width likely generalize.


The seminar will take place in the Common area, Old SISSA building, 
second floor - Via Beirut, 2

Indico: https://indico.ictp.it/event/11217/

You are all most welcome to attend!

Best regards,

Erica

Erica Sarnataro
Group Secretary
Quantitative Life Sciences
The Abdus Salam International Centre for Theoretical Physics (ICTP)
Trieste,  Italy
Tel. +39-040-22404623 (NEW PHONE NUMBER)
www.ictp.it/research/qls.aspx
e-mail:qls at ictp.it