BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Bernoulli Lecture - Empirical Optimal Transport: Inference\, Algor
 ithms\, Applications
DTSTART:20200528T171500
DTEND:20200528T181500
DTSTAMP:20260510T000031Z
UID:2f5e89f87e67335e2a0a3d46ccb04a372d9b79c83a86feeab33ebf41
CATEGORIES:Conferences - Seminars
DESCRIPTION:Axel Munk\, Georg-August-Universität Göttingen\nOptimal tra
 nsport has a long standing history in different branches of science\, orig
 inating from physics and logistics. Since its emergence as a rigorous math
 ematical concept in the last century it has influenced and shaped various 
 areas within mathematics but it also has been proven to a be a remarkably 
 rich and fruitful concept for various related disciplines\, such as econom
 ics and more recently computer science\, machine learning and statistics. 
 In this talk we discuss classical and more recent developments in statisti
 cal data analysis based on empirical optimal transport (EOT). Our mathemat
 ical fundament are limit laws and risk bounds for EOT plans and distances 
 on finite and discrete spaces. Proofs are based on a combination of sensit
 ivity analysis from convex optimization and discrete empirical process the
 ory. Theory will be used for statistical inference\, fast simulation\, and
  for fast randomized computation of optimal transport in large scale data 
 applications at pre-specified computational cost. EOT based data analysis 
 is illustrated in various computer experiments and on biological data from
  super-resolution cell microscopy.\n\nPart of the Semester : Functional D
 ata Analysis\n 
LOCATION:GA 3 21 https://plan.epfl.ch/?room==GA%203%2021
STATUS:CANCELLED
END:VEVENT
END:VCALENDAR