BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Talk of Professor Gabriel Peyré  (Ecole Normale Supérieure\, Par
 is).
DTSTART:20220915T111500
DTEND:20220915T120000
DTSTAMP:20260917T010730Z
UID:0687fb267dd6a57c043ceb6e4fe315379460239b37b9f3844b932972
CATEGORIES:Conferences - Seminars
DESCRIPTION:Dr Gabriel Peyré\, CNRS senior researcher and professor at th
 e Ecole Normale Supérieure\, Paris.\nTITLE: Scaling Optimal Transport for
  High dimensional Learning\n\nABSTRACT: Optimal transport (OT) has recent
 ly gained lot of interest in machine learning. It is a natural tool to com
 pare in a geometrically faithful way probability distributions. It finds a
 pplications in both supervised learning (using geometric loss functions) a
 nd unsupervised learning (to perform generative model fitting). OT is howe
 ver plagued by the curse of dimensionality\, since it might require a numb
 er of samples which grows exponentially with the dimension. In this talk\,
  I will explain how to leverage entropic regularization methods to define 
 computationally efficient loss functions\, approximating OT with a better 
 sample complexity. More information and references can be found on the web
 site of our book "Computational Optimal Transport" https://optimaltranspo
 rt.github.io/\n\nBIO: Gabriel Peyré is CNRS senior researcher and profess
 or at the Ecole Normale Supérieure\, Paris. He works at the interface bet
 ween applied mathematics\, imaging and machine learning. He obtained 2 ERC
  grants (starting in 2010 and consolidator in 2017)\, the Blaise Pascal pr
 ize from the French academy of sciences in 2017\, the Magenes Prize from t
 he Italian Mathematical Union in 2019 and the silver medal from CNRS in 20
 21. He is invited speaker at the European Congress for Mathematics in 2020
 . He is the deputy director of the Prairie Institute for artificial intell
 igence\, the director of the ENS center for data science and the former di
 rector of the GdR CNRS MIA. He is the head of the ELLIS (European Lab for 
 Learning & Intelligent Systems) Paris Unit. He is engaged in reproducible 
 research and code education\, in particular through the platform www.numer
 ical-tours.com.
LOCATION:BM 5202 https://plan.epfl.ch/?room==BM%205202 https://epfl.zoom.u
 s/j/81786690250
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR