BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:High Throughput Bayesian Optimisation - Victor Picheny (None / Oth
 er)
DTSTART:20230420T100000Z
DTEND:20230420T110000Z
UID:TALK199030@talks.cam.ac.uk
DESCRIPTION:Bayesian optimisation excels in small data regimes\, but its l
 arge computational overhead and the cubic cost of vanilla Gaussian Process
  models makes it impractical as soon as the data size reaches thousands of
  points. In this talk\, we will expose some of the work developed at Secon
 dmind\, fueled by real-world applications from the automotive industry\, t
 o expand the capability of Bayesian optimisation to tackle high data regim
 es (typically thousands to millions of observations). Leveraging sparse va
 riational GP models and Thompson sampling strategies\, we will demonstrate
  that Bayesian optimisation can enjoy both strong theoretical guarantees a
 nd empirical performance in this context.
LOCATION:Seminar Room 2\, Newton Institute
END:VEVENT
END:VCALENDAR