Sparsity oracle inequalities for the Lasso
Florentina Bunea, Alexandre B. Tsybakov, Marten H. Wegkamp · 2007
Abstract: This paper studies oracle properties of!1-penalized least squares in nonparametric regression setting with random design. We show that the penalized least squares estimator satisfies sparsity oracle inequalities, i.e., bounds in terms of the number of non-zero components of the oracle vec-tor. The results are valid even when the dimension of the model is (much) larger than the sample size and the regression matrix is not positive definite. They can be applied to high-dimensional linear regression, to nonparamet-ric adaptive regression estimation and to the problem of aggregation of arbitrary estimators.
Cited by 392 works.
Authors
References
- Regression Shrinkage and Selection Via the Lasso
- Ideal Spatial Adaptation by Wavelet Shrinkage
- Least angle regression
- Stable recovery of sparse overcomplete representations in the presence of noise
- High dimensional graphs and variable selection with the Lasso
- A new approach to variable selection in least squares problems
- Asymptotics for lasso-type estimators
- On Model Selection Consistency of Lasso
- On the LASSO and Its Dual
- A Distribution-Free Theory of Nonparametric Regression