BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Large Deviations Principle for Bures-Wasserstein Barycenters
DTSTART:20240524T151500
DTEND:20240524T161500
DTSTAMP:20260525T161942Z
UID:deafbd4a910b2ed1f2e223f6d297d9e18cefb6df37c258a7af0b7186
CATEGORIES:Conferences - Seminars
DESCRIPTION:Adam Jaffe\, UC Berkeley\nThe Bures-Wasserstein space of Gauss
 ian probability measures plays an important role in statistics and machine
  learning\, where it has recently been appreciated that a canonical notion
  of averaging Gaussian measures arises as computing barycenters in the Bur
 es-Wasserstein geometry. For empirical Bures-Wasserstein barycenters of in
 dependent\, identically-distributed samples\, much is known about their co
 nvergence to a population counterpart (strong law of large numbers\, centr
 al limit theorem\, rates of convergence\, concentration inequalities\, etc
 .).\n\nIn this talk\, we add to this story by proving the large deviations
  principle for Bures-Wasserstein barycenters\, which allows us to compute 
 the exact exponential rate of decay of many different rare events of inter
 est. We also give several statistical and probabilistic applications of th
 ese results.\n \n\n\n 
LOCATION:CM 1 517 https://plan.epfl.ch/?room==CM%201%20517
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR