Polar Gaussian Processes and Experimental Designs in Circular Domains

Abstract : Predicting on circular domains is a central issue that can be addressed by Gaus- sian process (GP) regression. However, usual GP models do not take into account the geometry of the disk in their covariance structure (or kernel), which may be a drawback at least for industrial processes involving a rotation or a diffusion from the center of the disk. We introduce so-called polar GPs defined on the space of polar coordinates. Their kernels are obtained as a combination of a kernel for the radius and a kernel for the angle, based on either chordal or geodesic distances on the circle. Their efficiency is illustrated on two industrial applications. We further consider the problem of designing experiments on the disk. Two new Latin hypercube designs are obtained, by defining a valid maximin criterion for polar coordinates. Finally, an extension of the whole methodology to higher dimensions is investigated.
Document type :
Preprints, Working Papers, ...
Liste complète des métadonnées

Cited literature [24 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01119942
Contributor : Olivier Roustant <>
Submitted on : Wednesday, March 30, 2016 - 5:18:23 PM
Last modification on : Tuesday, October 23, 2018 - 2:36:09 PM
Document(s) archivé(s) le : Monday, November 14, 2016 - 9:37:51 AM

File

polarGP_HAL.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01119942, version 4

Citation

Espéran Padonou, O Roustant. Polar Gaussian Processes and Experimental Designs in Circular Domains. 2016. ⟨hal-01119942v4⟩

Share

Metrics

Record views

488

Files downloads

535