A totally unimodular view of structured sparsity

@InProceedings{pmlr-v38-elhalabi15,
  title = 	 {{A totally unimodular view of structured sparsity}},
  author = 	 {El Halabi, Marwa and Cevher, Volkan},
  booktitle = 	 {Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics},
  pages = 	 {223--231},
  year = 	 {2015},
  editor = 	 {Lebanon, Guy and Vishwanathan, S. V. N.},
  volume = 	 {38},
  series = 	 {Proceedings of Machine Learning Research},
  address = 	 {San Diego, California, USA},
  month = 	 {09--12 May},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v38/elhalabi15.pdf},
  url = 	 {https://proceedings.mlr.press/v38/elhalabi15.html},
  abstract = 	 {This paper describes a simple framework for structured sparse recovery based on convex optimization. We show that many structured sparsity models can be naturally represented by linear matrix inequalities on the support of the unknown parameters, where the constraint matrix has a totally unimodular (TU) structure.  For such structured models, tight convex relaxations can be obtained in polynomial time via linear programming. Our modeling framework unifies the prevalent structured sparsity norms in the literature, introduces new interesting ones, and renders their tightness and tractability arguments transparent.}
}