Speaker
Dr
Paul SAVES
(DTIS, ONERA and Fédération ENAC ISAE-SUPAERO ONERA, Université de Toulouse, France)
Description
This talk presents a novel distance function and modeling framework for mixed-variable domains, effectively handling heterogeneous data with continuous, integer, and categorical variables, including meta variables that shape problem structure. This approach is presented in a paper that enhanced generalization and optimization in large representation models in science without partitioning data. A follow-up paper will extend this work by unifying surrogate modeling in architecture optimization, introducing graph-structured domains and partially decreed variables, with applications in green aeronautics via Bayesian optimization.
| Contribution length | Short |
|---|
Primary authors
Mr
Edward Hallé-Hannan
(GERAD and Department of Mathematics and Industrial Engineering, Polytechnique Montréal)
Dr
Paul SAVES
(DTIS, ONERA and Fédération ENAC ISAE-SUPAERO ONERA, Université de Toulouse, France)
Co-authors
Prof.
Charles Audet
(GERAD and Department of Mathematics and Industrial Engineering, Polytechnique Montréal)
Dr
Eric Nguyen Van
(DTIS, ONERA and Fédération ENAC ISAE-SUPAERO ONERA, Université de Toulouse, France)
Mr
Jasper Bussemaker
(German Aerospace Center (DLR))
Prof.
Joseph Morlier
(ISAE-SUPAERO and Institut Clément Ader, Université de Toulouse, France)
Prof.
Nathalie Bartoli
(DTIS, ONERA and Fédération ENAC ISAE-SUPAERO ONERA, Université de Toulouse, France)
Mr
Rémi Lafage
(DTIS, ONERA and Fédération ENAC ISAE-SUPAERO ONERA, Université de Toulouse, France)
Prof.
Sébastien Le Digabel
(GERAD and Department of Mathematics and Industrial Engineering, Polytechnique Montréal)
Mr
Thierry Lefebvre
(DTIS, ONERA and Fédération ENAC ISAE-SUPAERO ONERA, Université de Toulouse, France)
Dr
Youssef Diouane
(GERAD and Department of Mathematics and Industrial Engineering, Polytechnique Montréal)
