High-dimensional Polynomial Chaos Basis Selection with Bayesian Compressive Sensing

Abstract

For a complex model with a large number of input parameters, building
Polynomial Chaos (PC) surrogate models is challenged by insufficient
model simulation data as well as by a prohibitively large number of
spectral basis terms. Bayesian sparse learning approaches are
implemented in order to detect a sparse polynomial basis set that best
captures the model outputs. We enhanced the Bayesian compressive sensing approach with adaptive basis growth and with a data-driven, piecewise-PC surrogate construction.

Date
Jul 24, 2013
Location
Raleigh, NC