ML Anthology

A Nearly-Linear Time Framework for Graph-Structured Sparsity

Chinmay Hegde, Piotr Indyk, Ludwig Schmidt
IJCAI 2016 pp. 4165-4169
/ijcai/2016/hegde2016ijcai-nearly/

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, our framework achieves an information-theoretically optimal sample complexity for a wide range of parameters. We complement our theoretical analysis with experiments showing that our algorithms also improve on prior work in practice. PDF

PDF IJCAI Semantic Scholar

Cite

Text

Hegde et al. "A Nearly-Linear Time Framework for Graph-Structured Sparsity." International Joint Conference on Artificial Intelligence, 2016.

Markdown

[Hegde et al. "A Nearly-Linear Time Framework for Graph-Structured Sparsity." International Joint Conference on Artificial Intelligence, 2016.](https://mlanthology.org/ijcai/2016/hegde2016ijcai-nearly/)

BibTeX

@inproceedings{hegde2016ijcai-nearly,
  title     = {{A Nearly-Linear Time Framework for Graph-Structured Sparsity}},
  author    = {Hegde, Chinmay and Indyk, Piotr and Schmidt, Ludwig},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2016},
  pages     = {4165-4169},
  url       = {https://mlanthology.org/ijcai/2016/hegde2016ijcai-nearly/}
}