Derek Bingham
(Simon Fraser University)

Le vendredi 24 janvier 2014 / Friday, January 24, 2014

Calibration of computer experiments with large data structures

RESUME / ABSTRACT : Statistical model calibration of computer models is commonly done in a wide variety of scientific endeavours. In the end, this exercise amounts to solving an inverse problem and a form of regression.  Gaussian process model are very convenient in this setting as non-parametric regression estimators and provide sensible inference properties.  However, when the data structures are large, fitting the model becomes difficult.  In this work, new methodology for calibrating large computer experiments is presented. We proposed to perform the calibration exercise by modularizing a hierarchical statistical model with approximate emulation via local Gaussian processes.  The approach is motivated by an application to radiative shock hydrodynamics.


Salle / Room 1355
Centre de recherches mathématiques
Pavillon André-Aisenstadt
Université de Montréal
2920, chemin de la Tour

15 h 30 / 3:30 p.m.

Une réception suivra la conférence au Salon Maurice-l'Abbé
Pavillon André-Aisenstadt (Salle 6245)