International audienceAggregating estimators using exponential weights depending on their risk performs well in expectation, but sadly not in probability. A way to overcome this issue is considering exponential weights of a penalized risk. In this case, an oracle inequality can be obtained in probability, but is not sharp. Taking into account the estimated function's norm in the penalty offers a sharp inequality.L'agrégation d'estimateur a l'aide de poids exponentiels dépendant de leur risque offre de bonnes performances en moyenne. Malheureusement, il est impossible d'obtenir un aussi bon contrôle du risque de l'estimateur agrégé en probabilité. Pour contourner ce problème, nous considérons des poids exponentiels du risque pénalisé. Cette ...
International audienceWe consider the problem of combining a (possibly uncountably infinite) set of ...
In many areas of statistics, including signal and image processing, high-dimensional estimation is a...
Aggregating estimators using exponential weights depending on their risk appears optimal in expectat...
International audienceAggregating estimators using exponential weights depending on their risk perfo...
National audienceUn problème classique en traitement du signal et des images vise à estimer un signa...
National audienceUn problème classique en traitement du signal et des images vise à estimer un signa...
Dans plusieurs domaines des statistiques, y compris le traitement du signal et des images, l'estimat...
Ce manuscrit se concentre sur deux problèmes d'estimation de fonction. Pour chacun, une garantie non...
This manuscript focuses on two functional estimation problems. A non asymptotic guarantee of the pro...
We treat two subjects. The first subject is about statistical learning in high-dimension, that is wh...
Originally, oracle inequalities were developed as particularly efficient tools in mathematical stati...
International audienceThe main goal in this paper is to propose a new approach to deriving oracle in...
Abstract. We consider the sparse regression model where the number of pa-rameters p is larger than t...
International audienceWe study the problem of aggregation under the squared loss in the model of reg...
International audienceIn this paper, we consider a high-dimensional statistical estimation problem i...
International audienceWe consider the problem of combining a (possibly uncountably infinite) set of ...
In many areas of statistics, including signal and image processing, high-dimensional estimation is a...
Aggregating estimators using exponential weights depending on their risk appears optimal in expectat...
International audienceAggregating estimators using exponential weights depending on their risk perfo...
National audienceUn problème classique en traitement du signal et des images vise à estimer un signa...
National audienceUn problème classique en traitement du signal et des images vise à estimer un signa...
Dans plusieurs domaines des statistiques, y compris le traitement du signal et des images, l'estimat...
Ce manuscrit se concentre sur deux problèmes d'estimation de fonction. Pour chacun, une garantie non...
This manuscript focuses on two functional estimation problems. A non asymptotic guarantee of the pro...
We treat two subjects. The first subject is about statistical learning in high-dimension, that is wh...
Originally, oracle inequalities were developed as particularly efficient tools in mathematical stati...
International audienceThe main goal in this paper is to propose a new approach to deriving oracle in...
Abstract. We consider the sparse regression model where the number of pa-rameters p is larger than t...
International audienceWe study the problem of aggregation under the squared loss in the model of reg...
International audienceIn this paper, we consider a high-dimensional statistical estimation problem i...
International audienceWe consider the problem of combining a (possibly uncountably infinite) set of ...
In many areas of statistics, including signal and image processing, high-dimensional estimation is a...
Aggregating estimators using exponential weights depending on their risk appears optimal in expectat...