BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Inaugural lecture: Machine Learning Theory in the Age of AI Revolu
 tion
DTSTART:20230509T171500
DTEND:20230509T180000
DTSTAMP:20260609T100702Z
UID:4fe29954834f83e1b32cdcc4401e99475f864b8371647e664890861c
CATEGORIES:Inaugural lectures - Honorary Lecture
DESCRIPTION:Prof Florent Krzakala \nAbstract\nAs groundbreaking advancemen
 ts in artificial intelligence emerge every week\, the question arises: can
  theoreticians still contribute meaningfully to understanding these remark
 able engineering feats? Traditional foundations\, based on bias-variance t
 radeoffs\, convex optimization\, and data-agnostic theory\, struggle to ac
 commodate the complexities of modern methods. In this talk\, we will explo
 re how new ideas and directions at the intersection of high-dimensional pr
 obability\, statistical physics\, and information theory provide fresh per
 spectives on these challenges. By focusing on simple toy mathematically so
 lvable models\, we hope to gain a deeper understanding of the relationship
 s between data\, performance\, and algorithm.\n\n\nBio\nFlorent Krzakala i
 s a French physicist and applied mathematician\, currently a professor at 
 EPFL. His research focuses on using mathematical tools inspired by statist
 ical physics to solve theoretical problems in physics\, computer science\,
  machine learning\, statistics\, and signal processing. He received his Ph
 D in statistical physics jointly from Pierre and Marie Curie University an
 d Paris-Sud University in 2002. After a postdoc with Giorgio Parisi in Rom
 e\, he was a lecturer at ESPCI in Paris and then a professor at Sorbonne U
 niversity and the Ecole Normale Supérieure in Paris\, where he also held 
 the data science chair and founded the startup LightOn. He has held variou
 s visiting positions at universities in the United States and was named a 
 junior fellow of the Institut Universitaire de France in 2015. Krzakala le
 ads the Idephics laboratory at EPFL and is known in particular for his wor
 k on community detection\, quantum annealing\, and phase transitions in sa
 tisfiability and coloring problems\, as well as high-dimensional statistic
 s and algorithms.\n 
LOCATION:ELA 1 https://plan.epfl.ch/?room==ELA%201
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR