16 citations · 69 across the 27 of their papers we have counts for
36 papers
Riemannian Gradient Descent for Gaussian Mixture Models with unknown diagonal covariances
Romane Giard, Yohann De Castro, Roland Denis +1
This paper investigates the numerical resolution of the Beurling-LASSO (BLASSO), a convex optimization framework that promotes sparsity in the space of measures. We consider its ap…
Fenchel-Young Duality Gaps: Certified Early Stopping for Regularized Inverse Problems
Pierre-Cyril Aubin-Frankowski, Yohann de Castro
We study computable error bounds and certified early stopping for regularized inverse problems, where a data-fidelity term is traded against a regularizer. The analysis relies on a…
Fast Spawn\&Prune (FS\&P): Global convergence of stochastic conic particle gradient descent via birth/death process
Yohann De Castro, Sébastien Gadat, Clément Marteau
We investigate the global optimization of the objective function arising in continuous sparse regression, specifically the Beurling LASSO (BLASSO), over the space of measures. Whil…
Gaussian Mixture Model with unknown diagonal covariances via continuous sparse regularization
Romane Giard, Yohann de Castro, Clément Marteau
This paper addresses the statistical estimation of Gaussian Mixture Models (GMMs) with unknown diagonal covariances from independent and identically distributed samples. We employ…
Generalization Bounds of Surrogate Policies for Combinatorial Optimization Problems
Pierre-Cyril Aubin-Frankowski, Yohann De Castro, Axel Parmentier +1
Many real-world decision problems require solving, again and again, combinatorial optimization instances drawn from a common distribution. A recent line of structured learning meth…
Second Maximum of a Gaussian Random Field and Exact (t-)Spacing test
Jean-Marc Azaïs, Federico Dalmao, Yohann De Castro
In this article, we introduce the novel concept of the second maximum of a Gaussian random field defined on a Riemannian manifold: Once the field reaches its global maximum at a po…
FastPart: Over-Parameterized Stochastic Gradient Descent for Sparse optimisation on Measures
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 Gradien…
Exact recovery of the support of piecewise constant images via total variation regularization
Yohann De Castro, Vincent Duval, Romain Petit
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…
Neural Networks beyond explainability: Selective inference for sequence motifs
Antoine Villié, Philippe Veber, Yohann de Castro +1
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…
Random Geometric Graph: Some recent developments and perspectives
Quentin Duchemin, Yohann de Castro
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…
SIGLE: a valid procedure for Selective Inference with the Generalized Linear Lasso
Quentin Duchemin, Yohann de Castro
This article investigates uncertainty quantification of the generalized linear lasso~(GLL), a popular variable selection method in high-dimensional regression settings. In many fie…
Three rates of convergence or separation via U-statistics in a dependent framework
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. In a recent work, a new…
Minimax Estimation of Partially-Observed Vector AutoRegressions
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 corrupte…
Towards Off-the-grid Algorithms for Total Variation Regularized Inverse Problems
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. Contrary to most existing methods, that produce an…
Time series forecasting from partial observations via Non-negative Matrix Factorization
Yohann de Castro, Luca Mencarelli
In modern time series problems, one aims at forecasting multiple time series with possible missing and noisy values. In this paper, we introduce the Sliding Mask Method (SMM) for f…
Concentration inequality for U-statistics of order two for uniformly ergodic Markov chains
Quentin Duchemin, Yohann de Castro, Claire Lacour
We prove a new concentration inequality for U-statistics of order two for uniformly ergodic Markov chains. Working with bounded and -canonical kernels, we show that we can recov…
Markov Random Geometric Graph (MRGG): A Growth Model for Temporal Dynamic Networks
Quentin Duchemin, Yohann de Castro
We introduce Markov Random Geometric Graphs (MRGGs), a growth model for temporal dynamic networks. It is based on a Markovian latent space dynamic: consecutive latent points are sa…
Multiple Testing and Variable Selection along the path of the Least Angle Regression
J. -M. Azaïs, Y. De Castro
We investigate multiple testing and variable selection using the Least Angle Regression (LARS) algorithm in high dimensions under the assumption of Gaussian noise. LARS is known to…
Adaptive Estimation of Nonparametric Geometric Graphs
Yohann De Castro, Claire Lacour, Thanh Mai Pham Ngoc
This article studies the recovery of graphons when they are convolution kernels on compact (symmetric) metric spaces. This case is of particular interest since it covers the situat…
Approximate Optimal Designs for Multivariate Polynomial Regression
Yohann De Castro, Fabrice Gamboa, Didier Henrion +2
We introduce a new approach aiming at computing approximate optimal designs for multivariate polynomial regressions on compact (semi-algebraic) design spaces. We use the moment-sum…
Testing Gaussian Process with Applications to Super-Resolution
Jean-Marc Azaïs, Yohann De Castro, Stéphane Mourareau
This article introduces exact testing procedures on the mean of a Gaussian process derived from the outcomes of -minimization over the space of complex valued measures.…
Recovering Multiple Nonnegative Time Series From a Few Temporal Aggregates
Jiali Mei, Yohann De Castro, Yannig Goude +1
Motivated by electricity consumption metering, we extend existing nonnegative matrix factorization (NMF) algorithms to use linear measurements as observations, instead of matrix en…
Adapting to unknown noise level in sparse deconvolution
Claire Boyer, Yohann De Castro, Joseph Salmon
In this paper, we study sparse spike deconvolution over the space of complex-valued measures when the input measure is a finite sum of Dirac masses. We introduce a modified version…
Sparse Recovery from Extreme Eigenvalues Deviation Inequalities
Sandrine Dallaporta, Yohann De Castro
This article provides a new toolbox to derive sparse recovery guarantees from small deviations on extreme singular values or extreme eigenvalues obtained in Random Matrix Theory. T…