Convex relaxation for IMSE optimal design in random-field models

Abstract

The de nition of an Integrated Mean-Squared Error (IMSE) criterion for the learning of a random eld model yields a particular Karhunen-Loève expansion of the underlying eld. The model can thus also be interpreted as a Bayesian (or regularised) linear model based on eigenfunctions of this Karhunen-Loève expansion, and can be approximated by a linear model… (More)
DOI: 10.1016/j.csda.2016.10.018

Topics

9 Figures and Tables

Cite this paper

@article{Gauthier2017ConvexRF, title={Convex relaxation for IMSE optimal design in random-field models}, author={Bertrand Gauthier and Luc Pronzato}, journal={Computational Statistics & Data Analysis}, year={2017}, volume={113}, pages={375-394} }