BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Isaac Newton Institute Seminar Series
SUMMARY:Replication or exploration? Sequential design for 
 stochastic simulation experiments - Robert Gramacy
  (Virginia Polytechnic Institute and State Univers
 ity)
DTSTART;TZID=Europe/London:20180209T133000
DTEND;TZID=Europe/London:20180209T143000
UID:TALK100213AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/100213
DESCRIPTION:We investigate the merits of replication\, and pro
 vide methods that search for optimal designs (incl
 uding replicates)\, in the context of noisy comput
 er simulation experiments. We first show that repl
 ication offers the potential to be beneficial from
  both design and computational perspectives\, in t
 he context of Gaussian process surrogate modeling.
  We then develop a lookahead based sequential desi
 gn scheme that can determine if a new run should b
 e at an existing input location (i.e.\, replicate)
  or at a new one (explore). When paired with a new
 ly developed heteroskedastic Gaussian process mode
 l\, our dynamic design scheme facilitates learning
  of signal and noise relationships which can vary 
 throughout the input space. We show that it does s
 o efficiently\, on both computational and statisti
 cal grounds. In addition to illustrative synthetic
  examples\, we demonstrate performance on two chal
 lenging real-data simulation experiments\, from in
 ventory management and epidemiology.
LOCATION:Seminar Room 1\, Newton Institute
CONTACT:INI IT
END:VEVENT
END:VCALENDAR