Voir la notice de l'article provenant de la source Numdam
We consider the problem of estimating a function in logistic regression model. We propose to estimate this function by a sparse approximation build as a linear combination of elements of a given dictionary of functions. This sparse approximation is selected by the Lasso or Group Lasso procedure. In this context, we state non asymptotic oracle inequalities for Lasso and Group Lasso under restricted eigenvalue assumption as introduced in [P.J. Bickel, Y. Ritov and A.B. Tsybakov, Ann. Statist. 37 (2009) 1705–1732].
Kwemou, Marius 1, 2
@article{PS_2016__20__309_0, author = {Kwemou, Marius}, title = {Non-asymptotic oracle inequalities for the {Lasso} and {Group} {Lasso} in high dimensional logistic model}, journal = {ESAIM: Probability and Statistics}, pages = {309--331}, publisher = {EDP-Sciences}, volume = {20}, year = {2016}, doi = {10.1051/ps/2015020}, mrnumber = {3533711}, zbl = {1353.62054}, language = {en}, url = {http://geodesic.mathdoc.fr/articles/10.1051/ps/2015020/} }
TY - JOUR AU - Kwemou, Marius TI - Non-asymptotic oracle inequalities for the Lasso and Group Lasso in high dimensional logistic model JO - ESAIM: Probability and Statistics PY - 2016 SP - 309 EP - 331 VL - 20 PB - EDP-Sciences UR - http://geodesic.mathdoc.fr/articles/10.1051/ps/2015020/ DO - 10.1051/ps/2015020 LA - en ID - PS_2016__20__309_0 ER -
%0 Journal Article %A Kwemou, Marius %T Non-asymptotic oracle inequalities for the Lasso and Group Lasso in high dimensional logistic model %J ESAIM: Probability and Statistics %D 2016 %P 309-331 %V 20 %I EDP-Sciences %U http://geodesic.mathdoc.fr/articles/10.1051/ps/2015020/ %R 10.1051/ps/2015020 %G en %F PS_2016__20__309_0
Kwemou, Marius. Non-asymptotic oracle inequalities for the Lasso and Group Lasso in high dimensional logistic model. ESAIM: Probability and Statistics, Tome 20 (2016), pp. 309-331. doi: 10.1051/ps/2015020
Cité par Sources :