Zobrazeno 1 - 10
of 290
pro vyhledávání: '"P, Vayer"'
Estimating matrices in the symmetric positive-definite (SPD) cone is of interest for many applications ranging from computer vision to graph learning. While there exist various convex optimization-based estimators, they remain limited in expressivity
Externí odkaz:
http://arxiv.org/abs/2406.09023
Autor:
Van Assel, Hugues, Vincent-Cuaz, Cédric, Courty, Nicolas, Flamary, Rémi, Frossard, Pascal, Vayer, Titouan
Unsupervised learning aims to capture the underlying structure of potentially large and high-dimensional datasets. Traditionally, this involves using dimensionality reduction (DR) methods to project data onto lower-dimensional spaces or organizing po
Externí odkaz:
http://arxiv.org/abs/2402.02239
Autor:
Léger, Mélanie, Vayer, Florianne, Hatnean, Monica Ciomaga, Damay, Françoise, Decorse, Claudia, Berardan, David, Fåk, Björn, Zanotti, Jean-Marc, Berrod, Quentin, Embs, Jacques Ollivier Jan P., Fennell, Tom, Sheptyakov, Denis, Petit, Sylvain, Lhotel, Elsa
Publikováno v:
Phys. Rev. B 109, 224416 (2024)
We study the stability of the antiferromagnetic all-in--all-out state observed in dipolar-octupolar pyrochlores that have neodymium as the magnetic species. Different types of disorder are considered, either affecting the immediate environment of the
Externí odkaz:
http://arxiv.org/abs/2401.15027
We consider the problem of learning a graph modeling the statistical relations of the $d$ variables from a dataset with $n$ samples $X \in \mathbb{R}^{n \times d}$. Standard approaches amount to searching for a precision matrix $\Theta$ representativ
Externí odkaz:
http://arxiv.org/abs/2311.04673
We present a versatile adaptation of existing dimensionality reduction (DR) objectives, enabling the simultaneous reduction of both sample and feature sizes. Correspondances between input and embedding samples are computed through a semi-relaxed Grom
Externí odkaz:
http://arxiv.org/abs/2310.03398
Regularising the primal formulation of optimal transport (OT) with a strictly convex term leads to enhanced numerical complexity and a denser transport plan. Many formulations impose a global constraint on the transport plan, for instance by relying
Externí odkaz:
http://arxiv.org/abs/2310.02925
Publikováno v:
GRETSI 2023-XXIX{\`e}me Colloque Francophone de Traitement du Signal et des Images
We provide a framework and algorithm for tuning the hyperparameters of the Graphical Lasso via a bilevel optimization problem solved with a first-order method. In particular, we derive the Jacobian of the Graphical Lasso solution with respect to its
Externí odkaz:
http://arxiv.org/abs/2307.02130
Many approaches in machine learning rely on a weighted graph to encode the similarities between samples in a dataset. Entropic affinities (EAs), which are notably used in the popular Dimensionality Reduction (DR) algorithm t-SNE, are particular insta
Externí odkaz:
http://arxiv.org/abs/2305.13797
Autor:
Florianne Vayer, Sylvain Petit, Françoise Damay, Jan Embs, Stéphane Rols, Claire Colin, Elsa Lhotel, Dalila Bounoua, Nita Dragoe, David Bérardan, Claudia Decorse
Publikováno v:
Communications Materials, Vol 5, Iss 1, Pp 1-10 (2024)
Abstract Two decades of work have shown that the physics of Tb-based pyrochlores is controlled by a subtle equilibrium between quadrupole-quadrupole and dipolar-dipolar magnetic interactions, as exemplified by the ordered spin ice Tb2Sn2O7 and the qu
Externí odkaz:
https://doaj.org/article/f47782e0075248f993fbf8881ac0ddc3
Dimension reduction (DR) methods provide systematic approaches for analyzing high-dimensional data. A key requirement for DR is to incorporate global dependencies among original and embedded samples while preserving clusters in the embedding space. T
Externí odkaz:
http://arxiv.org/abs/2303.05119