no code implementations • 10 Dec 2023 • Yohann de Castro, Sébastien Gadat, Clément Marteau
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 problems on measures.
no code implementations • 23 Dec 2022 • Antoine Villié, Philippe Veber, Yohann de Castro, Laurent Jacob
Over the past decade, neural networks have been successful at making predictions from biological sequences, especially in the context of regulatory genomics.
no code implementations • 24 Jun 2021 • Quentin Duchemin, Yohann de Castro, Claire Lacour
Despite the ubiquity of U-statistics in modern Probability and Statistics, their non-asymptotic analysis in a dependent framework may have been overlooked.
1 code implementation • 17 Jun 2021 • Guillaume Dalle, Yohann de Castro
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 harder?
1 code implementation • 14 Apr 2021 • Yohann de Castro, Vincent Duval, Romain Petit
We introduce an algorithm to solve linear inverse problems regularized with the total (gradient) variation in a gridless manner.
no code implementations • 10 Feb 2021 • Yohann de Castro, Luca Mencarelli
Based on recent advances in Nonnegative Matrix Factorization (NMF) and Archetypal Analysis, we introduce two procedures referred to as Sliding Mask Method (SMM) and Latent Clustered Forecast (LCF).
1 code implementation • 20 Nov 2020 • Quentin Duchemin, Yohann de Castro, Claire Lacour
We prove a new concentration inequality for U-statistics of order two for uniformly ergodic Markov chains.
no code implementations • 8 Sep 2020 • Yohann de Castro, Fabrice Gamboa, Didier Henrion, Jean Lasserre
The purpose of this short note is to show that the Christoffel-Darboux polynomial, useful in approximation theory and data science, arises naturally when deriving the dual to the problem of semi-algebraic D-optimal experimental design in statistics.
Optimization and Control Statistics Theory Statistics Theory
no code implementations • 12 Jun 2020 • Quentin Duchemin, Yohann de Castro
It is based on a Markovian latent space dynamic: consecutive latent points are sampled on the Euclidean Sphere using an unknown Markov kernel; and two nodes are connected with a probability depending on a unknown function of their latent geodesic distance.
1 code implementation • NeurIPS 2019 • Ernesto Araya, Yohann de Castro
We introduce a spectral estimator of the pairwise distance between latent points and we prove that its rate of convergence is the same as the nonparametric estimation of a function on $\mathbb{S}^{d-1}$, up to a logarithmic factor.
no code implementations • 23 Jul 2019 • Yohann de Castro, Sébastien Gadat, Clément Marteau, Cathy Maugis
This paper investigates the statistical estimation of a discrete mixing measure $\mu$0 involved in a kernel mixture model.
no code implementations • 19 Sep 2017 • Jiali Mei, Yohann de Castro, Yannig Goude, Jean-Marc Azaïs, Georges Hébrail
Motivated by the reconstruction and the prediction of electricity consumption, we extend Nonnegative Matrix Factorization~(NMF) to take into account side information (column or row features).
no code implementations • ICML 2017 • Jiali Mei, Yohann de Castro, Yannig Goude, Georges Hébrail
Motivated by electricity consumption reconstitution, we propose a new matrix recovery method using nonnegative matrix factorization (NMF).
1 code implementation • 9 Jun 2017 • Yohann De Castro, Fabrice Gamboa, Didier Henrion, Roxana Hess, Jean-Bernard Lasserre
We introduce a new approach aiming at computing approximate optimal designs for multivariate polynomial regressions on compact (semi-algebraic) design spaces.
Statistics Theory Information Theory Information Theory Numerical Analysis Computation Methodology Statistics Theory 62K05, 90C25 (Primary) 41A10, 49M29, 90C90, 15A15 (secondary)
1 code implementation • 2 Jun 2017 • Jean-Marc Azaïs, Yohann de Castro, Stéphane Mourareau
This article introduces exact testing procedures on the mean of a Gaussian process $X$ derived from the outcomes of $\ell_1$-minimization over the space of complex valued measures.
Statistics Theory Information Theory Information Theory Probability Statistics Theory 62E15, 62F03, 60G15, 62H10, 62H15 (Primary) 60E05, 60G10, 62J05, 94A08 (secondary)
no code implementations • 5 Oct 2016 • Jiali Mei, Yohann de Castro, Yannig Goude, Georges Hébrail
Motivated by electricity consumption metering, we extend existing nonnegative matrix factorization (NMF) algorithms to use linear measurements as observations, instead of matrix entries.
no code implementations • 5 Apr 2016 • Sandrine Dallaporta, Yohann de Castro
One benefit of this paper is a direct and explicit derivation of upper bounds on RICs and lower bounds on SRSR from small deviations on the extreme eigenvalues given by Random Matrix theory.
no code implementations • 26 Mar 2016 • Yohann De Castro, Thibault Espinasse, Paul Rochet
In this paper, we aim at recovering an undirected weighted graph of $N$ vertices from the knowledge of a perturbed version of the eigenspaces of its adjacency matrix $W$.
no code implementations • 12 Oct 2010 • Yohann de Castro
We investigate the high-dimensional regression problem using adjacency matrices of unbalanced expander graphs.