This thesis explores properties of estimations procedures related to aggregation in the problem of high-dimensional regression in a sparse setting. The exponentially weighted aggregate (EWA) is well studied in the literature. It benefits from strong results in fixed and random designs with a PAC-Bayesian approach. However, little is known about the properties of the EWA with Laplace prior. Chapter 2 analyses the statistical behaviour of the prediction loss of the EWA with Laplace prior in the fixed design setting. Sharp oracle inequalities which generalize the properties of the Lasso to a larger family of estimators are established. These results also bridge the gap from the Lasso to the Bayesian Lasso. Chapter 3 introduces an adjusted Lang...
AbstractWe consider the problem of regression learning for deterministic design and independent rand...
Short version published in COLT 2009International audienceWe consider the problem of regression lear...
In this thesis, we consider the linear regression model in the high dimensional setup. In particular...
This thesis explores properties of estimations procedures related to aggregation in the problem of h...
This thesis explores properties of estimations procedures related to aggregation in the problem of h...
This thesis explores properties of estimations procedures related to aggregation in the problem of h...
This thesis explores properties of estimations procedures related to aggregation in the problem of h...
Les travaux de cette thèse explorent les propriétés de procédures d'estimation par agrégation appliq...
AbstractWe consider the problem of regression learning for deterministic design and independent rand...
Short version published in COLT 2009International audienceWe consider the problem of regression lear...
Short version published in COLT 2009International audienceWe consider the problem of regression lear...
Short version published in COLT 2009International audienceWe consider the problem of regression lear...
Short version published in COLT 2009International audienceWe consider the problem of regression lear...
We consider the problem of regression learning for deterministic design and independent random er-ro...
Short version published in COLT 2009International audienceWe consider the problem of regression lear...
AbstractWe consider the problem of regression learning for deterministic design and independent rand...
Short version published in COLT 2009International audienceWe consider the problem of regression lear...
In this thesis, we consider the linear regression model in the high dimensional setup. In particular...
This thesis explores properties of estimations procedures related to aggregation in the problem of h...
This thesis explores properties of estimations procedures related to aggregation in the problem of h...
This thesis explores properties of estimations procedures related to aggregation in the problem of h...
This thesis explores properties of estimations procedures related to aggregation in the problem of h...
Les travaux de cette thèse explorent les propriétés de procédures d'estimation par agrégation appliq...
AbstractWe consider the problem of regression learning for deterministic design and independent rand...
Short version published in COLT 2009International audienceWe consider the problem of regression lear...
Short version published in COLT 2009International audienceWe consider the problem of regression lear...
Short version published in COLT 2009International audienceWe consider the problem of regression lear...
Short version published in COLT 2009International audienceWe consider the problem of regression lear...
We consider the problem of regression learning for deterministic design and independent random er-ro...
Short version published in COLT 2009International audienceWe consider the problem of regression lear...
AbstractWe consider the problem of regression learning for deterministic design and independent rand...
Short version published in COLT 2009International audienceWe consider the problem of regression lear...
In this thesis, we consider the linear regression model in the high dimensional setup. In particular...