Zobrazeno 1 - 10
of 4 263
pro vyhledávání: '"Arnáiz, A."'
Ensembles of Deep Neural Networks, Deep Ensembles, are widely used as a simple way to boost predictive performance. However, their impact on algorithmic fairness is not well understood yet. Algorithmic fairness investigates how a model's performance
Externí odkaz:
http://arxiv.org/abs/2410.13831
Autor:
Arnaiz, Victor, Rivière, Gabriel
On the unit tangent bundle of a compact Riemannian surface, we consider a natural sub-Riemannian Laplacian associated with the canonical contact structure. In the large eigenvalue limit, we study the escape of mass at infinity in the cotangent space
Externí odkaz:
http://arxiv.org/abs/2306.10757
Social networks contribute to the distribution of social capital, defined as the relationships, norms of trust and reciprocity within a community or society that facilitate cooperation and collective action. Social capital exists in the relations amo
Externí odkaz:
http://arxiv.org/abs/2305.03223
Algorithmic fairness is of utmost societal importance, yet state-of-the-art large-scale machine learning models require training with massive datasets that are frequently biased. In this context, pre-processing methods that focus on modeling and corr
Externí odkaz:
http://arxiv.org/abs/2303.01928
Autor:
Arnaiz, Victor
In this work we consider the KAM renormalizability problem for small pseudodifferential perturbations of the semiclassical isochronous transport operator with Diophantine frequencies on the torus. Assuming that the symbol of the perturbation is real
Externí odkaz:
http://arxiv.org/abs/2301.12728
Autor:
Arnaiz, Víctor, Macià, Fabricio
In this work, concentration properties of quasimodes for perturbed semiclassical harmonic oscillators are studied. The starting point of this research comes from the fact that, in the presence of resonances between frequencies of the harmonic oscilla
Externí odkaz:
http://arxiv.org/abs/2206.10307
Publikováno v:
Proceedings of the First Learning on Graphs Conference (LoG 2022), PMLR 198, Virtual Event, December, 2022
Graph Neural Networks (GNNs) have been shown to achieve competitive results to tackle graph-related tasks, such as node and graph classification, link prediction and node and graph clustering in a variety of domains. Most GNNs use a message passing f
Externí odkaz:
http://arxiv.org/abs/2206.07369
Publikováno v:
Health and Human Rights, 2023 Jun 01. 25(1), 9-22.
Externí odkaz:
https://www.jstor.org/stable/48732652
Autor:
Mendibil, Unai, Lópiz-Morales, Yaiza, Arnaiz, Blanca, Ruiz-Hernández, Raquel, Martín, Pablo, Di-Silvio, Desiré, Garcia-Urquia, Nerea, Elortza, Felix, Azkargorta, Mikel, Olalde, Beatriz, Abarrategi, Ander
Publikováno v:
In Materials Today Bio October 2024 28
Autor:
Luque, Sonia, Mendoza-Palomar, Natalia, Aguilera-Alonso, David, Garrido, Beatriz, Miarons, Marta, Piqueras, Ana Isabel, Tévar, Enrique, Velasco-Arnaiz, Eneritz, Fernàndez-Polo, Aurora
Publikováno v:
In Farmacia Hospitalaria September-October 2024 48(5):T234-T245