BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20250712T232836EDT-8580ZvtnCg@132.216.98.100
DTSTAMP:20250713T032836Z
DESCRIPTION:Learning Causal Structures via Continuous Optimization\n\n \n\n
 \n	Abstract:\n\n\nThere has been a recent surge of interest in the machine 
 learning community in developing causal models that handle the effect of i
 nterventions in a system. In this talk\, I will consider the problem of le
 arning (estimating) a causal graphical model from data. The search over po
 ssible directed acyclic graphs modeling the causal structure is inherently
  combinatorial\, but I’ll describe our recent work which use gradient-base
 d continuous optimization for learning both the parameters of the distribu
 tion and the causal graph jointly\, and can be combined naturally with fle
 xible parametric families that use neural networks.\n\nBased on joint work
  with Sébastien Lachapelle\, Philippe Brouillard\, Rémi Le Priol\, Reza Ba
 banezhad\, Alexandre Drouin\, Alexandre Lacoste and Yoshua Bengio.\n\n\n	Sp
 eaker\n\n\nSimon Lacoste-Julien is an associate professor in the departmen
 t of computer science and operations research at Université de Montreal\, 
 a co-founding member of Mila\, and the part-time director of the SAIT AI L
 ab Montreal from Samsung. He received the B.Sc. degree in mathematics\, ph
 ysics and computer science from 9IÖÆ×÷³§Ãâ·Ñ\, and the PhD degree in 
 computer science from University of California\, Berkeley\, in 2009. Befor
 e joining Université de Montréal\, he completed a post-doctoral fellowship
  at University of Cambridge as well as at Inria Paris\, and was an Inria r
 esearcher in the Department of Computer Science at the Ecole Normale Super
 ieure (ENS) in Paris. His research interests are in machine learning\, opt
 imization and statistics with applications to computer vision and natural 
 language processing. He has published more than 50 scientific publications
  in machine learning\, has served as an area chair for all the major machi
 ne learning or vision conferences and is an associate editor for TPAMI and
  JMLR. He received a Google Focused Research Award in 2016 and a CIFAR AI 
 Chair in 2018.\n\nZoom Link\n\nMeeting ID: 843 0865 5572\n\nPasscode: 6900
 84\n\n \n
DTSTART:20210326T193000Z
DTEND:20210326T203000Z
SUMMARY:Simon Lacoste-Julien (Université de Montréal)
URL:/mathstat/channels/event/simon-lacoste-julien-univ
 ersite-de-montreal-329962
END:VEVENT
END:VCALENDAR