BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20250712T084849EDT-07850xjk3V@132.216.98.100
DTSTAMP:20250712T124849Z
DESCRIPTION:\n	\n		\n			\n				TITLE / TITRE\n\n				Free lunches and subsampling Monte Car
 lo\n					\n					ABSTRACT/RÉSUMÉ \n\n				It is well-known that the performance of MCMC al
 gorithms degrades quite quickly when targeting computationally expensive p
 osterior distributions\, including the posteriors for even simple models w
 hen the dataset is large. This has motivated the search for MCMC variants 
 that scale well for large datasets. One simple approach\, taken by several
  research groups\, has been to look at only a subsample of the data at eve
 ry step. This method is known to work quite well for optimization\, and va
 riants of stochastic gradient descent are the workhorse of modern machine 
 learning. In this talk\, we focus on a simple 'no-free-lunch' result which
  shows that no algorithm of this sort can provide substantial speedups for
  Bayesian computation. We briefly sketch the main steps in the proof\, ill
 ustrate how these generic results apply to realistic statistical problems 
 and proposed algorithms\, and discuss some special examples that can avoid
  our generic results and provide a free (or at least cheap) lunch. We also
  mention recent work 'in both directions\,' extending our basic conclusion
  to some non-reversible chains and showing explicitly how it can be avoide
 d for more complex posteriors (Based on joint with Patrick Conrad\, Andrew
  Davis\, James Johndrow\, Zonghao Li\, Youssef Marzouk\, Natesh Pillai\, P
 engfei Wang and Azeem Zaman.)\n\n				PLACE / LIEU\n\n				Hybride - CRM\, Salle / R
 oom 5340\, Pavillon André Aisenstadt\n			\n		\n	\n\n
DTSTART:20241129T203000Z
DTEND:20241129T213000Z
LOCATION:Burnside Hall\, CA\, QC\, Montreal\, H3A 0B9\, 805 rue Sherbrooke 
 Ouest
SUMMARY:Aaron Smith (University of Ottawa)
URL:/mathstat/channels/event/aaron-smith-university-ot
 tawa-361371
END:VEVENT
END:VCALENDAR