BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Worst-Case Learning from Inaccurate Data and under Multifidelity M
 odels - Simon  Foucart  (Texas A&M University)
DTSTART:20240715T103000Z
DTEND:20240715T111000Z
UID:TALK218122@talks.cam.ac.uk
DESCRIPTION:This talk showcases the speaker's recent results in the field 
 of Optimal Recovery\, viewed as a trustworthy Learning Theory focusing on 
 the worst case. At the core of several results presented here is a scenari
 o\, resolved in the global and the local settings\, where the model set is
  the intersection of two hyperellipsoids. This has implications in optimal
  recovery from deterministically inaccurate data and in optimal recovery u
 nder a multifidelity-inspired model. In both situations\, the theory becom
 es richer when considering the optimal estimation of linear functionals. T
 his particular case also comes with additional results in the presence of 
 randomly inaccurate data.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR