Reducing dimension in Bayesian Optimization
Résumé
This talk was first given at the LIMOS on July the 9th 2020 and was mainly intended for an audience of non specialists of Gaussian processes (GPs). It was then updated for the GDR MascotNum ETICS2020 school in October and the Webinar Data analytics \& AI at Mines Telecom in November.
The first slides (up to slide 12) about GPs and Bayesian Optimization should probably be skipped by readers already aware about these topics.
The review of dimension reduction techniques is an attempt at providing a unified point of view on this ubiquitous topic.
The two research contributions on variable selection for optimization 1) by kernel methods and, 2) by penalized likelihood in a mapped space, may be of interest to many experts.
Origine | Fichiers produits par l'(les) auteur(s) |
---|