1k citations
- Université Toulouse III - Paul SabatierFR936 papers
- Centre National de la Recherche ScientifiqueFR543 papers
- Institut National des Sciences Appliquées de ToulouseFR543 papers
- Université de ToulouseFR306 papers
- Toulouse Mathematics Institute172 papers
- Université Fédérale de Toulouse Midi-PyrénéesFR155 papers
- Institut Universitaire de FranceFR37 papers
- Institut national de recherche en sciences et technologies du numériqueFR35 papers
- Laboratoire de Mathématiques d'OrsayFR34 papers
- Institut de Mathématiques de BordeauxFR31 papers
- Institut de Mathématiques de Jussieu-Paris Rive GaucheFR27 papers
- Laboratoire d'Analyse et d'Architecture des SystèmesFR27 papers
9 papers · 2 filters
Posterior contraction rates for constrained deep Gaussian processes in density estimation and classication
François Bachoc, Agnès Lagnoux
We provide posterior contraction rates for constrained deep Gaussian processes in non-parametric density estimation and classication. The constraints are in the form of bounds on t…
Bounds in Wasserstein distance on the normal approximation of general M-estimators
François Bachoc, Max Fathi
We derive quantitative bounds on the rate of convergence in Wasserstein distance of general M-estimators, with an almost sharp (up to a logarithmic term) behavior in the numb…
Existence, Stability and Scalability of Orthogonal Convolutional Neural Networks
El Mehdi Achour, François Malgouyres, Franck Mamalet
Imposing orthogonality on the layers of neural networks is known to facilitate the learning by limiting the exploding/vanishing of the gradient; decorrelate the features; improve t…
The loss landscape of deep linear neural networks: a second-order analysis
El Mehdi Achour, François Malgouyres, Sébastien Gerchinovitz
We study the optimization landscape of deep linear neural networks with the square loss. It is known that, under weak assumptions, there are no spurious local minima and no local m…
Optimal use of auxiliary information : information geometry and empirical process
Sofiane Arradi-Alaoui
We incorporate into the empirical measure the auxiliary information given by a finite collection of expectation in an optimal information geometry way. This allows to unify several…
Central Limit Theorems for General Transportation Costs
Eustasio del Barrio, Alberto González-Sanz, Jean-Michel Loubes
We consider the problem of optimal transportation with general cost between a empirical measure and a general target probability on R d , with d 1. We extend results in [19]…