International audienceWe consider the problem of combining a (possibly uncountably infinite) set of affine estimators in non-parametric regression model with heteroscedastic Gaussian noise. Focusing on the exponentially weighted aggregate, we prove a PAC-Bayesian type inequality that leads to sharp oracle inequalities in discrete but also in continuous settings. The framework is general enough to cover the combinations of various procedures such as least square regression, kernel ridge regression, shrinking estimators and many other estimators used in the literature on statistical inverse problems. As a consequence, we show that the proposed aggregate provides an adaptive estimator in the exact minimax sense without neither discretizing the...
This PhD thesis studies two fields of Statistics: Aggregation of estimatorsand shape constrained reg...
We consider the problem of regression learning for deterministic design and independent random er-ro...
Originally, oracle inequalities were developed as particularly efficient tools in mathematical stati...
International audienceWe consider the problem of combining a (possibly uncountably infinite) set of ...
International audienceWe consider the problem of combining a (possibly uncountably infinite) set of ...
Aggregating estimators using exponential weights depending on their risk appears optimal in expectat...
We consider the problem of aggregating a general collection of affine estimators for fixed design re...
Abstract: We consider the problem of aggregating a general collection of affine estimators for fixed...
International audienceIn this paper, we consider a high-dimensional statistical estimation problem i...
Abstract. We consider the sparse regression model where the number of pa-rameters p is larger than t...
International audienceAn adaptive nonparametric estimation procedure is constructed for heteroscedas...
International audienceAn adaptive nonparametric estimation procedure is constructed for the estimati...
International audienceIn this paper, we consider a high-dimensional non-parametric regression model ...
This manuscript focuses on two functional estimation problems. A non asymptotic guarantee of the pro...
We consider the sparse regression model where the number of parameters $p$ is larger than the sample...
This PhD thesis studies two fields of Statistics: Aggregation of estimatorsand shape constrained reg...
We consider the problem of regression learning for deterministic design and independent random er-ro...
Originally, oracle inequalities were developed as particularly efficient tools in mathematical stati...
International audienceWe consider the problem of combining a (possibly uncountably infinite) set of ...
International audienceWe consider the problem of combining a (possibly uncountably infinite) set of ...
Aggregating estimators using exponential weights depending on their risk appears optimal in expectat...
We consider the problem of aggregating a general collection of affine estimators for fixed design re...
Abstract: We consider the problem of aggregating a general collection of affine estimators for fixed...
International audienceIn this paper, we consider a high-dimensional statistical estimation problem i...
Abstract. We consider the sparse regression model where the number of pa-rameters p is larger than t...
International audienceAn adaptive nonparametric estimation procedure is constructed for heteroscedas...
International audienceAn adaptive nonparametric estimation procedure is constructed for the estimati...
International audienceIn this paper, we consider a high-dimensional non-parametric regression model ...
This manuscript focuses on two functional estimation problems. A non asymptotic guarantee of the pro...
We consider the sparse regression model where the number of parameters $p$ is larger than the sample...
This PhD thesis studies two fields of Statistics: Aggregation of estimatorsand shape constrained reg...
We consider the problem of regression learning for deterministic design and independent random er-ro...
Originally, oracle inequalities were developed as particularly efficient tools in mathematical stati...