Shared active subspace for multivariate vector-valued functions

Autor: Musayeva, Khadija, Binois, Mickael

This paper proposes several approaches as baselines to compute a shared active subspace for multivariate vector-valued functions. The goal is to minimize the deviation between the function evaluations on the original space and those on the reconstruc

Externí odkaz: http://arxiv.org/abs/2401.02735

Sample Complexity Result for Multi-category Classifiers of Bounded Variation

Autor: Musayeva, Khadija

We control the probability of the uniform deviation between empirical and generalization performances of multi-category classifiers by an empirical L1 -norm covering number when these performances are defined on the basis of the truncated hinge loss

Externí odkaz: http://arxiv.org/abs/2003.09176

Revisiting Multi-Label Propagation: the Case of Small Data

Autor: Musayeva, Khadija, Binois, Mickael

This paper focuses on multi-label learning from small number of labelled data. We demonstrate that the straightforward binary-relevance extension of the interpolated label propagation algorithm, the harmonic function, is a competitive learning method

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::f15423d0d216e2f8204cc158cf435739
https://inria.hal.science/hal-03914733/file/musayevabinois22.pdf

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Metric entropy and Rademacher complexity of margin multi-category classifiers

Autor: Musayeva, Khadija, Lauer, Fabien, Guermeur, Yann

Publikováno v: 26th International Conference on Artificial Neural Networks (ICANN)
26th International Conference on Artificial Neural Networks (ICANN), Sep 2017, Alghero, Italy. pp.767

International audience

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::690305f6105be7eab552314dc229be89
https://hal.archives-ouvertes.fr/hal-03011347