BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20251121T024549EST-9080zSIpTV@132.216.98.100
DTSTAMP:20251121T074549Z
DESCRIPTION:Title: Can uncertainty be quantified? On confident hallucinatio
 ns in deep learning-based methods for inverse problems\n\nAbstract:\n\nDee
 p learning is currently transforming how inverse problems arising in imagi
 ng reconstruction are solved. However\, it is increasingly well-known that
  such deep learning-based methods are susceptible to hallucinations. In th
 is talk\, I will present a series of theoretical explanations for why hall
 ucinations occur\, in both deterministic and statistical estimators. I wil
 l conclude by observing that hallucinations can only be avoided by careful
  design of the forwards operator in tandem with the recovery algorithm\, a
 nd then provide a theoretical framework for how this can be achieved when 
 solving inverse problems using generative models.\n\nSpeaker\n\nBen Adcock
  is a Professor of Mathematics at Simon Fraser University. He studied math
 ematics at the University of Cambridge\, where he received his PhD in 2011
  as a member of the Numerical Analysis group under the supervision of Arie
 h Iserles.\n\nHe has received numerous awards\, including the CAIMS/PIMS E
 arly Career Award (2017)\, an Alfred P. Sloan Research Fellowship (2015)\,
  and a Leslie Fox Prize in Numerical Analysis (2011). Professor Adcock has
  authored and co-authored three books and monographs. Among them\, his boo
 k Compressive Imaging: Structure\, Sampling\, Learning was a finalist for 
 the Association of American Publishers Awards for Professional and Scholar
 ly Excellence (PROSE Awards).\n\nHe serves on the Board of Directors of th
 e Society for the Foundations of Computational Mathematics and is a member
  of the editorial boards of the SIAM Journal on Scientific Computing\, the
  IMA Journal of Numerical Analysis\, Numerische Mathematik\, the Journal o
 f Approximation Theory\, the SIAM Computational Science and Engineering bo
 ok series\, and the CMS/CAIMS Books in Mathematics series (Springer).\n
DTSTART:20251114T203000Z
DTEND:20251114T213000Z
LOCATION:Room 1104\, Burnside Hall\, CA\, QC\, Montreal\, H3A 0B9\, 805 rue
  Sherbrooke Ouest
SUMMARY:Ben Adcock (Simon Fraser University)
URL:/mathstat/channels/event/ben-adcock-simon-fraser-u
 niversity-368829
END:VEVENT
END:VCALENDAR