BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Primal-dual subgradient method for convex problems with functional
  constraints
DTSTART:20141114T111500
DTEND:20141114T120000
DTSTAMP:20260501T133731Z
UID:3e2f77beb4441dfc9af2576101603f130bcf6e428d3da358d92313b5
CATEGORIES:Conferences - Seminars
DESCRIPTION:Yurii Nesterov\, Ecole Polytechnique de Louvain\nAbstract\nIn 
 this talk we present a new primal-dual method for solving nonsmooth constr
 ained optimization problem with functional constraints. This method consis
 ts in parallel updates of primal and dual variables\, such that the dual u
 pdates can be seen as a coordinate descent scheme. Nevertheless\, it has b
 est possible performance guarantees. We show that such a method can be app
 lied to sparse problems of very big size\, ensuring the logarithmic depend
 ence of iteration complexity in the problem’s dimension.BiographyYurii N
 esterov is a professor at Center for Operations Research and Econometrics 
 (CORE) in the Catholic University of Louvain (UCL)\, Belgium. He received 
 his Ph.D. degree (Applied Mathematics) in 1984 at the Institute of Control
  Sciences\, Moscow. His research interests are related to complexity issue
 s and efficient methods for solving various optimization problems. His mai
 n research interestes are in Convex Optimization (optimal methods for smoo
 th problems\, polynomial-time interior-point methods\, smoothing technique
  for structural optimization\, cubic regularization of Newton method\, opt
 imization methods for huge-scale problems).
LOCATION:CM 1 2 https://plan.epfl.ch/?room==CM%201%202
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR