BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20260611T063122EDT-53798R89lM@132.216.98.100
DTSTAMP:20260611T103122Z
DESCRIPTION:Some development on dynamic computer experiments\n\nComputer ex
 periments refer to the study of real systems using complex simulation mode
 ls. They have been widely used as efficient\, economical alternatives to p
 hysical experiments. Computer experiments with time series outputs are cal
 led dynamic computer experiments. In this talk\, we consider two problems 
 of such experiments: emulation of large-scale dynamic computer experiments
  and inverse problem. For the first problem\, we proposed a computationall
 y efficient modelling approach which sequentially finds a set of local des
 ign points based on a new criterion specifically designed for emulating dy
 namic computer simulators. Singular value decomposition based Gaussian pro
 cess models are built with the sequentially chosen local data. To update t
 he models efficiently\, an empirical Bayesian approach is introduced. The 
 second problem aims to extract an optimal input of dynamic computer simula
 tor whose response matches a field observation as closely as possible. A s
 equential design approach is employed and a novel expected improvement cri
 terion is proposed. A real application is discussed to support the efficie
 ncy of the proposed approaches. This is joint work with Ru Zhang at Queen’
 s University and Pritam Ranjan at Indian Institute of Management Indore.\n
 \n \n
DTSTART:20180323T193000Z
DTEND:20180323T203000Z
LOCATION:Room 1205\, Burnside Hall\, CA\, QC\, Montreal\, H3A 0B9\, 805 rue
  Sherbrooke Ouest
SUMMARY:C. Devon Lin (Queen's University)
URL:https://www.mcgill.ca/mathstat/channels/event/c-devon-lin-queens-univer
 sity-285928
END:VEVENT
END:VCALENDAR