2012

Non-asymptotic Oracle Inequalities for the Lasso and Group Lasso in high dimensional logistic model

Kwemou, Marius

Understand

We consider the problem of estimating a function $f\_{0}$ in logistic regression model.

We propose to estimate this function $f\_{0}$ by a sparse approximation build as a linear combination of elements of a given dictionary of $p$ 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 eigenvalues assumption as introduced in \cite{BRT}.

Built on

Information theory and an extension of the maximum likelihood principle
H. Akaike · 1973
Earlier work this paper cites.
Estimating the dimension of a model
Gideon Schwarz · 1978
Earlier work this paper cites.
Non-parametric logistic regression
T Hastie · 1983
Earlier work this paper cites.
Interior-point polynomial algorithms in convex programming
Yurii Nesterov and Arkadii Nemirovskii · 1994
Earlier work this paper cites.
Regression shrinkage and selection via the lasso
Robert Tibshirani · 1996
Earlier work this paper cites.
Asymptotics for lasso-type estimators
Keith Knight and Wenjiang Fu · 2000
Earlier work this paper cites.
A new approach to variable selection in least squares problems
M. R. Osborne, Brett Presnell, and B. A. Turlach · 2000
Earlier work this paper cites.
Concentration inequalities and model selection
Pascal Massart · 2003
Earlier work this paper cites.
Concentration inequalities
S. Boucheron, G. Lugosi, and O. Bousquet · 2004
Earlier work this paper cites.
Subband correlation and robust speech recognition
J. McAuley, J. Ming, D. Stewart, and P. Hanna · 2005
Earlier work this paper cites.
Aggregation and sparsity via l 1 l_{1} penalized least squares
Florentina Bunea, Alexandre B. Tsybakov, and Marten H. Wegkamp · 2006
Earlier work this paper cites.
High-dimensional graphs and variable selection with the lasso
Nicolai Meinshausen and Peter Bühlmann · 2006
Earlier work this paper cites.
Classifiers of support vector machine type with l 1 l_{1} complexity regularization
Bernadetta Tarigan and Sara A. van de Geer · 2006
Earlier work this paper cites.
Model selection and estimation in regression with grouped variables
Ming Yuan and Yi Lin · 2006
Earlier work this paper cites.

Similar

On model selection consistency of Lasso
Peng Zhao and Bin Yu · 2006
Cited alongside, same era.
The adaptive lasso and its oracle properties
Hui Zou · 2006
Cited alongside, same era.
Sparsity oracle inequalities for the Lasso
Florentina Bunea, Alexandre Tsybakov, and Marten Wegkamp · 2007
Cited alongside, same era.
Aggregation for Gaussian regression
Florentina Bunea, Alexandre B. Tsybakov, and Marten H. Wegkamp · 2007
Cited alongside, same era.
L 1 L_{1} -regularization path algorithm for generalized linear models
Mee Young Park and Trevor Hastie · 2007
Cited alongside, same era.
Some theoretical results on the grouped variables lasso
C. Chesneau and M. Hebiri · 2008
Cited alongside, same era.
The iterated lasso for high–dimensional logistic regression
J. Huang, S. Ma, and CH Zhang · 2008
Cited alongside, same era.
The group Lasso for logistic regression
Lukas Meier, Sara van de Geer, and Peter Bühlmann · 2008
Cited alongside, same era.
On the asymptotic properties of the group lasso estimator for linear models
Y. Nardi and A. Rinaldo · 2008
Cited alongside, same era.
High-dimensional generalized linear models and the lasso
Sara A. van de Geer · 2008
Cited alongside, same era.
The sparsity and bias of the LASSO selection in high-dimensional linear regression
Cun-Hui Zhang and Jian Huang · 2008
Cited alongside, same era.
Simultaneous analysis of lasso and Dantzig selector
Peter J. Bickel, Ya’acov Ritov, and Alexandre B. Tsybakov · 2009
Cited alongside, same era.

Then

High-dimensional additive modeling
L. Meier, S. Van De Geer, and P. Bühlmann · 2009
Later among the works it cites.
Lasso-type recovery of sparse representations for high-dimensional data
Nicolai Meinshausen and Bin Yu · 2009
Later among the works it cites.
Sparse additive models
P. Ravikumar, J. Lafferty, H. Liu, and L. Wasserman · 2009
Later among the works it cites.
On the conditions used to prove oracle results for the Lasso
Sara A. van de Geer and Peter Bühlmann · 2009
Later among the works it cites.
Genome-wide association analysis by lasso penalized logistic regression
T.T. Wu, Y.F. Chen, T. Hastie, E. Sobel, and K. Lange · 2009
Later among the works it cites.
Self-concordant analysis for logistic regression
Francis Bach · 2010
Later among the works it cites.
Regularization paths for generalized linear models via coordinate descent
J. Friedman, T. Hastie, and R. Tibshirani · 2010
Later among the works it cites.
Lasso logistic regression, GSoft and the cyclic coordinate descent algorithm: application to gene expression data
Manuel Garcia-Magariños, Anestis Antoniadis, Ricardo Cao, and Wenceslao González-Manteiga · 2010
Later among the works it cites.
Variable selection in nonparametric additive models
J. Huang, J.L. Horowitz, and F. Wei · 2010
Later among the works it cites.
Oracle inequalities and optimal inference under group sparsity
Karim Lounici, Massimiliano Pontil, Sara van de Geer, and Alexandre B. Tsybakov · 2011
Later among the works it cites.
The Lasso as an ℓ 1 \ell_{1} -ball model selection procedure
Pascal Massart and Caroline Meynet · 2011
Later among the works it cites.
L1-regularized linear regression: persistence and oracle inequalities
Peter L Bartlett, Shahar Mendelson, and Joseph Neeman · 2012
Closest in time.
A unified framework for high-dimensional analysis of M M -estimators with decomposable regularizers
Sahand N. Negahban, Pradeep Ravikumar, Martin J. Wainwright, and Bin Yu · 2012
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…