Quasi-Likelihood and/or Robust Estimation in High Dimensions
Authors:
- Sara van de GeerSGSara van de Geer
- Patric MüllerPMPatric Müller
Open Access
- 1 November 2012
- journal article
- Published by Institute of Mathematical Statistics in Statistical Science
- Vol. 27 (4) , 469-480
Abstract
We consider the theory for the high-dimensional generalized linear model with the Lasso. After a short review on theoretical results in literature, we present an extension of the oracle results to the case of quasi-likelihood loss. We prove bounds for the prediction error and $\ell_{1}$-error. The results are derived under fourth moment conditions on the error distribution. The case of robust loss is also given. We moreover show that under an irrepresentable condition, the $\ell_{1}$-penalized quasi-likelihood estimator has no false positives.Keywords
All Related Versions
This publication has 32 references indexed in Scilit:
- A Unified Framework for High-Dimensional Analysis of $M$-Estimators with Decomposable RegularizersStatistical Science, 2012
- Accuracy Guarantees for $\ell_1$-RecoveryIEEE Transactions on Information Theory, 2011
- Robust regression through the Huber’s criterion and adaptive lasso penaltyElectronic Journal of Statistics, 2011
- The adaptive and the thresholded Lasso for potentially misspecified models (and a lower bound for the Lasso)Electronic Journal of Statistics, 2011
- The Dantzig selector and sparsity oracle inequalitiesBernoulli, 2009
- Genome-wide association analysis by lasso penalized logistic regressionBioinformatics, 2009
- On the conditions used to prove oracle results for the LassoElectronic Journal of Statistics, 2009
- Sup-norm convergence rate and sign concentration property of Lasso and Dantzig estimatorsElectronic Journal of Statistics, 2008
- Aggregation for Gaussian regressionThe Annals of Statistics, 2007
- Sparsity oracle inequalities for the LassoElectronic Journal of Statistics, 2007