BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:The power of two samples in Generative Adversarial Networks (GAN).
DTSTART:20180109T110000
DTEND:20180109T120000
DTSTAMP:20260916T055712Z
UID:f959cd31ee4857089183ef08a78382488acbe6b3cdf6177b70dcecee
CATEGORIES:Conferences - Seminars
DESCRIPTION:Sewoong Oh\, Professor Assistant\, UIUC\n\nWe bring the tools 
 from Blackwell's seminal result in 1958 on comparing two stochastic experi
 ments\, to shine new lights on a modern  applications of great interest: 
 generative adversarial networks (GAN). Binary hypothesis testing is at the
  center of this application\, and we propose new data processing inequalit
 ies that allows us to discover new algorithms\, provide sharper analyses\,
  and provide simpler proofs. This leads to a new framework to handle one o
 f the major challenges in GAN known as ``mode collapse''\; the lack of div
 ersity in the samples generated by the learned generators. The hypothesis 
 testing view of GAN allows us to make a fundamental connection between our
  proposed idea of "packing" and mode collapse\, suggesting that packing is
  the right framework to deal with mode collapse\, when training GANs. For 
 this talk\, I will assume no prior background on GAN. 
LOCATION:INR 113 https://plan.epfl.ch/?room=INR113
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR