136 citations
- Aix-Marseille UniversitéFR68 papers
- Centre National de la Recherche ScientifiqueFR68 papers
- Laboratoire d'Informatique Fondamentale d'Orléans14 papers
- Laboratoire d’Informatique et SystèmesFR10 papers
- Institut national de recherche en sciences et technologies du numériqueFR8 papers
- Institut de Mathématiques de MarseilleFR7 papers
- King's College LondonGB7 papers
- Laboratoire Bordelais de Recherche en InformatiqueFR6 papers
- Laboratoire d'Informatique, de Modélisation et d'Optimisation des SystèmesFR6 papers
- École Normale Supérieure Paris-SaclayFR5 papers
- Fafo FoundationNO5 papers
- Technische Universität BerlinDE5 papers
4 papers · 2 filters
Dimension-free Concentration Bounds on Hankel Matrices for Spectral Learning
François Denis, Mattias Gybels, Amaury Habrard
Learning probabilistic models over strings is an important issue for many applications. Spectral methods propose elegant solutions to the problem of inferring weighted automata fro…
Online Learning with Multiple Operator-valued Kernels
Julien Audiffren, Hachem Kadri
We consider the problem of learning a vector-valued function f in an online learning setting. The function f is assumed to lie in a reproducing Hilbert space of operator-valued ker…
Stability of Multi-Task Kernel Regression Algorithms
Julien Audiffren, Hachem Kadri
We study the stability properties of nonlinear multi-task regression in reproducing Hilbert spaces with operator-valued kernels. Such kernels, a.k.a. multi-task kernels, are approp…
On multi-class learning through the minimization of the confusion matrix norm
Sokol Koço, Cécile Capponi
In imbalanced multi-class classification problems, the misclassification rate as an error measure may not be a relevant choice. Several methods have been developed where the perfor…