Zobrazeno 1 - 10
of 1 511
pro vyhledávání: '"A. Martínez Rubio"'
We study first-order algorithms that are uniformly stable for empirical risk minimization (ERM) problems that are convex and smooth with respect to $p$-norms, $p \geq 1$. We propose a black-box reduction method that, by employing properties of unifor
Externí odkaz:
http://arxiv.org/abs/2412.15956
We develop algorithms for the optimization of convex objectives that have H\"older continuous $q$-th derivatives with respect to a $p$-norm by using a $q$-th order oracle, for $p, q \geq 1$. We can also optimize other structured functions. We do this
Externí odkaz:
http://arxiv.org/abs/2411.08987
In this work, we analyze two of the most fundamental algorithms in geodesically convex optimization: Riemannian gradient descent and (possibly inexact) Riemannian proximal point. We quantify their rates of convergence and produce different variants w
Externí odkaz:
http://arxiv.org/abs/2403.10429
Autor:
Serrano, Sergio, Barrio, Roberto, Martínez-Rubio, Álvaro, Belmonte-Beitia, Juan, Pérez-García, Víctor M.
Chimeric Antigen Receptor T (CAR-T) cell therapy has been proven to be successful against different leukaemias and lymphomas. This paper makes an analytical and numerical study of a mathematical model describing the competition of CAR-T, leukaemias t
Externí odkaz:
http://arxiv.org/abs/2403.00340
Autor:
Scieur, Damien, Martínez-Rubio, David, Kerdreux, Thomas, d'Aspremont, Alexandre, Pokutta, Sebastian
Curvature properties of convex objects, such as strong convexity, are important in designing and analyzing convex optimization algorithms in the Hilbertian or Riemannian settings. In the case of the Hilbertian setting, strongly convex sets are well s
Externí odkaz:
http://arxiv.org/abs/2312.03583
Publikováno v:
Proceedings of Thirty Sixth Conference on Learning Theory (COLT 2023): https://proceedings.mlr.press/v195/criscitiello23b.html
Let $f \colon \mathcal{M} \to \mathbb{R}$ be a Lipschitz and geodesically convex function defined on a $d$-dimensional Riemannian manifold $\mathcal{M}$. Does there exist a first-order deterministic algorithm which (a) uses at most $O(\mathrm{poly}(d
Externí odkaz:
http://arxiv.org/abs/2307.12743
In this work, we study optimization problems of the form $\min_x \max_y f(x, y)$, where $f(x, y)$ is defined on a product Riemannian manifold $\mathcal{M} \times \mathcal{N}$ and is $\mu_x$-strongly geodesically convex (g-convex) in $x$ and $\mu_y$-s
Externí odkaz:
http://arxiv.org/abs/2305.16186
Autor:
Cristina Escamilla-Robla, Elisa Giménez-Fita, Natura Colomer-Pérez, David Martínez-Rubio, Jaime Navarrete
Publikováno v:
European Journal of Psychology Applied to Legal Context, Vol 16, Iss 2, Pp 87-96 (2024)
Background/Aim: The number of convictions related to crimes against road safety continues to increase, with more than half being caused by driving under the influence (DUI) of alcohol or drugs. In Spain, offenders for crimes against road safety have
Externí odkaz:
https://doaj.org/article/28d01b1c982c40a28136ecaf42f246b8
It has recently been shown that ISTA, an unaccelerated optimization method, presents sparse updates for the $\ell_1$-regularized personalized PageRank problem, leading to cheap iteration complexity and providing the same guarantees as the approximate
Externí odkaz:
http://arxiv.org/abs/2303.12875
Autor:
Espasa-Labrador, Javier1,2,3,4 (AUTHOR) javierespasa@roadtoperformance.com, Martínez-Rubio, Carlos5,6 (AUTHOR) carloscmrubio@gmail.com, Oliva-Lozano, José María7 (AUTHOR) jol908@ual.es, Calleja-González, Julio8,9 (AUTHOR) julio.calleja.gonzalez@gmail.com, Carrasco-Marginet, Marta1 (AUTHOR) mcarrascom@gencat.cat, Fort-Vanmeerhaeghe, Azahara10,11 (AUTHOR) azaharafv@blanquerna.url.edu
Publikováno v:
Sensors (14248220). Oct2024, Vol. 24 Issue 19, p6365. 18p.