Zobrazeno 1 - 10
of 119
pro vyhledávání: '"De Castro, Yohann"'
A recent stream of structured learning approaches has improved the practical state of the art for a range of combinatorial optimization problems with complex objectives encountered in operations research. Such approaches train policies that chain a s
Externí odkaz:
http://arxiv.org/abs/2407.17200
In this article, we introduce the novel concept of the second maximum of a Gaussian random field on a Riemannian submanifold. This second maximum serves as a powerful tool for characterizing the distribution of the maximum. By utilizing an ad-hoc Kac
Externí odkaz:
http://arxiv.org/abs/2406.18397
This paper presents a novel algorithm that leverages Stochastic Gradient Descent strategies in conjunction with Random Features to augment the scalability of Conic Particle Gradient Descent (CPGD) specifically tailored for solving sparse optimisation
Externí odkaz:
http://arxiv.org/abs/2312.05993
This work is concerned with the recovery of piecewise constant images from noisy linear measurements. We study the noise robustness of a variational reconstruction method, which is based on total (gradient) variation regularization. We show that, if
Externí odkaz:
http://arxiv.org/abs/2307.03709
Over the past decade, neural networks have been successful at making predictions from biological sequences, especially in the context of regulatory genomics. As in other fields of deep learning, tools have been devised to extract features such as seq
Externí odkaz:
http://arxiv.org/abs/2212.12542
Autor:
Duchemin, Quentin, de Castro, Yohann
The Random Geometric Graph (RGG) is a random graph model for network data with an underlying spatial representation. Geometry endows RGGs with a rich dependence structure and often leads to desirable properties of real-world networks such as the smal
Externí odkaz:
http://arxiv.org/abs/2203.15351
Autor:
Duchemin, Quentin, de Castro, Yohann
This article investigates uncertainty quantification of the generalized linear lasso~(GLL), a popular variable selection method in high-dimensional regression settings. In many fields of study, researchers use data-driven methods to select a subset o
Externí odkaz:
http://arxiv.org/abs/2203.15348
Publikováno v:
Journal of Machine Learning Research 23 (2022) 1-59
Despite the ubiquity of U-statistics in modern Probability and Statistics, their non-asymptotic analysis in a dependent framework may have been overlooked. In a recent work, a new concentration inequality for U-statistics of order two for uniformly e
Externí odkaz:
http://arxiv.org/abs/2106.12796
Autor:
Dalle, Guillaume, de Castro, Yohann
High-dimensional time series are a core ingredient of the statistical modeling toolkit, for which numerous estimation methods are known.But when observations are scarce or corrupted, the learning task becomes much harder.The question is: how much har
Externí odkaz:
http://arxiv.org/abs/2106.09327
We introduce an algorithm to solve linear inverse problems regularized with the total (gradient) variation in a gridless manner. Contrary to most existing methods, that produce an approximate solution which is piecewise constant on a fixed mesh, our
Externí odkaz:
http://arxiv.org/abs/2104.06706