BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Bayesian optimization / Gaussian Process Bandits - Sattar Vakili (
 MediaTek Research)
DTSTART:20210120T110000Z
DTEND:20210120T123000Z
UID:TALK153916@talks.cam.ac.uk
CONTACT:Elre Oldewage
DESCRIPTION:Sequential optimization is one of the fastest growing areas of
  machine learning. In this presentation we deep dive into sequential optim
 ization based on Gaussian process models (aka Bayesian optimization). We w
 ill take a look at the analysis of popular algorithms such as UCB and Thom
 pson sampling and wrap up with an overview of recent results and open prob
 lems. \n\nRecommended reading:\n\nSrinivas et al. 2010 (https://arxiv.org/
 abs/0912.3995)\, recipient of ICML 2020 Test of Time award\nChowdhury and 
 Gopalan 2017 (https://arxiv.org/abs/1704.00445)\nVakili et al. 2020 (https
 ://arxiv.org/abs/2009.06966)\nWilson et al. 2020 (https://arxiv.org/abs/20
 02.09309)
LOCATION:https://eng-cam.zoom.us/j/86068703738?pwd=YnFleXFQOE1qR1h6Vmtwbno
 0LzFHdz09
END:VEVENT
END:VCALENDAR