Nous montrons que la fonction de Christoffel empirique associée à un échantillon fini de points peut fournir un outil simple pour la classification supervisée en analyse de données, avec de bonnes propriétés de généralisation.
We show that the empirical Christoffel function associated with a cloud of finitely many points sampled from a distribution, can provide a simple tool for supervised classification in data analysis, with good generalization properties.
Révisé le :
Accepté le :
Publié le :
Jean B. Lasserre 1
@article{CRMATH_2022__360_G8_919_0, author = {Jean B. Lasserre}, title = {On the {Christoffel} function and classification in data analysis}, journal = {Comptes Rendus. Math\'ematique}, pages = {919--928}, publisher = {Acad\'emie des sciences, Paris}, volume = {360}, year = {2022}, doi = {10.5802/crmath.358}, language = {en}, }
Jean B. Lasserre. On the Christoffel function and classification in data analysis. Comptes Rendus. Mathématique, Volume 360 (2022), pp. 919-928. doi : 10.5802/crmath.358. https://comptes-rendus.academie-sciences.fr/mathematique/articles/10.5802/crmath.358/
[1] Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control, Cambridge University Press, 2019
[2] Sorting out typicality via the inverse moment matrix SOS polynomial, Advances in Neural Information Processing Systems (2016), pp. 190-198
[3] The empirical Christoffel function with applications in data analysis, Adv. Comput. Math., Volume 45 (2019) no. 3, pp. 1439-1468
[4] The Christoffel–Darboux Kernel for Data Analysis, Cambridge Monographs on Applied and Computational Mathematics, 38, Cambridge University Press, 2022 | Zbl
[5] Semi-algebraic approximation using Christoffel–Darboux kernel, Constr. Approx., Volume 54 (2021) no. 3, pp. 391-429
Cité par Sources :
Commentaires - Politique