Intersecting Singularities for Multi-Structured Estimation
Abstract
We address the problem of designing a convex nonsmooth regularizer encouraging multiple structural effects simultaneously. Focusing on the inference of sparse and low-rank matrices we suggest a new complexity index and a convex penalty approximating it. The new penalty term can be written as the trace norm of a linear function of the matrix. By analyzing theoretical properties of this family of regularizers we come up with oracle inequalities and compressed sensing results ensuring the quality of our regularized estimator. We also provide algorithms and supporting numerical experiments.
Cite
Text
Richard et al. "Intersecting Singularities for Multi-Structured Estimation." International Conference on Machine Learning, 2013.Markdown
[Richard et al. "Intersecting Singularities for Multi-Structured Estimation." International Conference on Machine Learning, 2013.](https://mlanthology.org/icml/2013/richard2013icml-intersecting/)BibTeX
@inproceedings{richard2013icml-intersecting,
title = {{Intersecting Singularities for Multi-Structured Estimation}},
author = {Richard, Emile and Bach, Francis and Vert, Jean-Philippe},
booktitle = {International Conference on Machine Learning},
year = {2013},
pages = {1157-1165},
volume = {28},
url = {https://mlanthology.org/icml/2013/richard2013icml-intersecting/}
}