Learning Heteroscedastic Models by Convex Programming under Group Sparsity
Abstract
Popular sparse estimation methods based on -relaxation, such as the Lasso and the Dantzig selector, require the knowledge of the variance of the noise in order to properly tune the regularization parameter. This constitutes a major obstacle in applying these methods in several frameworks---such as time series, random fields, inverse problems---for which the noise is rarely homoscedastic and its level is hard to know in advance. In this paper, we propose a new approach to the joint estimation of the conditional mean and the conditional variance in a high-dimensional (auto-) regression setting. An attractive feature of the proposed estimator is that it is efficiently computable even for very large scale problems by solving a second-order cone program (SOCP). We present theoretical analysis and numerical results assessing the performance of the proposed procedure.
Cite
@article{arxiv.1304.4549,
title = {Learning Heteroscedastic Models by Convex Programming under Group Sparsity},
author = {Arnak S. Dalalyan and Mohamed Hebiri and Katia Méziani and Joseph Salmon},
journal= {arXiv preprint arXiv:1304.4549},
year = {2013}
}
Comments
Proceedings of the 30 th International Conference on Machine Learning (2013) http://icml.cc/2013/?page_id=43