BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Understanding Machine Learning via Exactly Solvable Statistical Ph
 ysics Models
DTSTART:20230503T121500
DTEND:20230503T134500
DTSTAMP:20260430T055211Z
UID:1072081f9deb348149e5c55217e72babf2e085a55a51e0054e691341
CATEGORIES:Conferences - Seminars
DESCRIPTION:Lenka Zdeborová\nThe affinity between statistical physics and
  machine learning has a long history. I will describe the main lines of
  this long-lasting friendship in the context of current theoretical challe
 nges and open questions about deep learning. Theoretical physics often pr
 oceeds in terms of solvable synthetic models\, I will describe the relat
 ed line of work on solvable models of simple feed-forward neural network
 s. I will highlight a path forward to capture the subtle interplay between
  the structure of the data\, the architecture of the network\, and the opt
 imization algorithms commonly used for learning.  \n 
LOCATION:BSP 234 https://plan.epfl.ch/?room==BSP%20234
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR