High-dimensional stochastic optimization with the generalized Dantzig estimator - Mathematics > Statistics TheoryReport as inadecuate




High-dimensional stochastic optimization with the generalized Dantzig estimator - Mathematics > Statistics Theory - Download this document for free, or read online. Document in PDF available to download.

Abstract: We propose a generalized version of the Dantzig selector. We show that itsatisfies sparsity oracle inequalities in prediction and estimation. Weconsider then the particular case of high-dimensional linear regression modelselection with the Huber loss function. In this case we derive the sup-normconvergence rate and the sign concentration property of the Dantzig estimatorsunder a mutual coherence assumption on the dictionary.



Author: Karim Lounici PMA

Source: https://arxiv.org/







Related documents