BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Coordinate descent algorithms for convex optimization
DTSTART:20170809T100000
DTEND:20170809T120000
DTSTAMP:20260406T214413Z
UID:4be45dc053712b8405c378c3413a8dadca435fb99e5beb96ad06deac
CATEGORIES:Conferences - Seminars
DESCRIPTION:Sai Praneeth Karimireddy \nEDIC candidacy exam\nExam presiden
 t: Prof. Volkan Cevher\nThesis advisor: Prof. Martin Jaggi\nCo-examiner: P
 rof. Daniel Kuhn\n\nAbstract\nCoordinate descent algorithms are the workho
 rse of convex optimization in practice since they are easy to implement\, 
 fast\, and hard to beat. We want to design even faster coordinate descent 
 algorithms which take geometry\, communication costs etc. into account.\n\
 nBackground papers\nEfficiency of coordinate descent methods on huge-scale
  optimization problems\, by Nesterov\, Yu - SIAM Journal on Optimization 2
 2.2 (2012): 341-362.\nSDNA: Stochastic Dual Newton Ascent for Empirical Ri
 sk Minimization\, by Qu\, Zheng\, et al. - Proceedings of The 33rd Intern
 ational Conference on Machine Learning. 2016.  \nEfficiency of the Accel
 erated Coordinate Descent Method on Structured Optimization Problems\, by 
 Nesterov\, Yurii\, and Sebastian U. Stich. SIAM Journal on Optimization 27
 .1 (2017): 110-123.\n\n 
LOCATION:INJ 328 https://plan.epfl.ch/theme/generalite_thm_plan_public?lan
 g=en&room=INJ%20328&dim_floor=3&dim_lang=en&baselayer_ref=grp_backgrounds&
 tree_groups=centres_nevralgiques%2Cacces%2Cmobilite_reduite%2Censeign
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR