A Nearly-Linear Time Framework for Graph-Structured Sparsity
Abstract
We introduce a framework for sparsity structures defined via graphs. Our approach is flexible and generalizes several previously studied sparsity models. Moreover, we provide efficient projection algorithms for our sparsity model that run in nearly-linear time. In the context of sparse recovery, we show that our framework achieves an information-theoretically optimal sample complexity for a wide range of parameters. We complement our theoretical analysis with experiments demonstrating that our algorithms improve on prior work also in practice.
Cite
Text
Hegde et al. "A Nearly-Linear Time Framework for Graph-Structured Sparsity." International Conference on Machine Learning, 2015.Markdown
[Hegde et al. "A Nearly-Linear Time Framework for Graph-Structured Sparsity." International Conference on Machine Learning, 2015.](https://mlanthology.org/icml/2015/hegde2015icml-nearlylinear/)BibTeX
@inproceedings{hegde2015icml-nearlylinear,
title = {{A Nearly-Linear Time Framework for Graph-Structured Sparsity}},
author = {Hegde, Chinmay and Indyk, Piotr and Schmidt, Ludwig},
booktitle = {International Conference on Machine Learning},
year = {2015},
pages = {928-937},
volume = {37},
url = {https://mlanthology.org/icml/2015/hegde2015icml-nearlylinear/}
}