BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Florent Krzakala (EPFL)
DTSTART:20201028T180000Z
DTEND:20201028T190000Z
DTSTAMP:20260513T193025Z
UID:MPML/20
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/MPML/20/">So
 me exactly solvable models for statistical machine learning</a>\nby Floren
 t Krzakala (EPFL) as part of Mathematics\, Physics and Machine Learning (I
 ST\, Lisbon)\n\n\nAbstract\nThe increasing dimensionality of data in the m
 odern machine learning age presents new challenges and opportunities. The 
 high-dimensional settings allow one to use powerful asymptotic methods fro
 m probability theory and statistical physics to obtain precise characteriz
 ations and develop new algorithmic approaches. There is indeed a decades-l
 ong tradition in statistical physics with building and solving such simpli
 fied models of neural networks.\n\nI will give examples of recent works th
 at build on powerful methods of physics of disordered systems to analyze d
 ifferent problems in machine learning and neural networks\, including over
 parameterization\, kernel methods\, and the gradient descent algorithm in 
 a high dimensional non-convex setting.\n
LOCATION:https://researchseminars.org/talk/MPML/20/
END:VEVENT
END:VCALENDAR