BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:IC Colloquium: Optimization and Monte Carlo Sampling in Large Scal
 e Machine Learning
DTSTART:20190314T101500
DTEND:20190314T111500
DTSTAMP:20260406T185308Z
UID:b984a05100db1ef38bf37d125d86a00e1111ec1e2a2dd5fe81560db7
CATEGORIES:Conferences - Seminars
DESCRIPTION:By: Nicolas Flammarion - UC Berkeley\nIC Faculty candidate\n\n
 Abstract:\nOptimization algorithms and Monte Carlo sampling algorithms hav
 e provided the computational foundations for the rapid growth in applicati
 ons of machine learning in recent years. In this talk we will see how the 
 interplay between gradients\, stochastic and acceleration can be exploited
  to obtain fast and efficient statistical procedures.\nTo begin we present
  the first algorithm which achieves jointly optimal prediction rates both 
 in term of computational speed and statistical efficiency. This new algori
 thm is based on combining both averaging and acceleration.\nSecond\, we sh
 ow how sampling algorithms can be seen as optimization algorithms in the s
 pace of measures. Using this perspective\, we interpret the underdamped La
 ngevin algorithm as performing accelerated gradient descent on the KL dive
 rgence. The power of this approach allows us to obtain faster convergence 
 rates for non convex sampling problems.\n\nBio:\nNicolas Flammarion is a p
 ostdoctoral fellow in computer science at UC Berkeley\, hosted by Michael 
 I. Jordan. He received his PhD in 2017 from Ecole Normale Supérieur in Pa
 ris\, where he was advised by Alexandre d'Aspremont and Francis Bach. In 2
 018\, he received the prize of the Fondation Mathematique Jacques Hadamard
  for the best PhD thesis in the field of optimization. His research focuse
 s primarily on learning problems at the interface of machine learning and 
 optimization.\n\nMore information
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR