Skip to Main content Skip to Navigation
Journal articles

Convex and Network Flow Optimization for Structured Sparsity

Julien Mairal 1, * Rodolphe Jenatton 2, 3 Guillaume Obozinski 2, 3 Francis Bach 2, 3
* Corresponding author
3 SIERRA - Statistical Machine Learning and Parsimony
DI-ENS - Département d'informatique de l'École normale supérieure, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
Abstract : We consider a class of learning problems regularized by a structured sparsity-inducing norm defined as the sum of l_2- or l_infinity-norms over groups of variables. Whereas much effort has been put in developing fast optimization techniques when the groups are disjoint or embedded in a hierarchy, we address here the case of general overlapping groups. To this end, we present two different strategies: On the one hand, we show that the proximal operator associated with a sum of l_infinity-norms can be computed exactly in polynomial time by solving a quadratic min-cost flow problem, allowing the use of accelerated proximal gradient methods. On the other hand, we use proximal splitting techniques, and address an equivalent formulation with non-overlapping groups, but in higher dimension and with additional constraints. We propose efficient and scalable algorithms exploiting these two strategies, which are significantly faster than alternative approaches. We illustrate these methods with several problems such as CUR matrix factorization, multi-task learning of tree-structured dictionaries, background subtraction in video sequences, image denoising with wavelets, and topographic dictionary learning of natural image patches.
Complete list of metadata

Cited literature [84 references]  Display  Hide  Download

https://hal.inria.fr/inria-00584817
Contributor : Julien Mairal <>
Submitted on : Thursday, September 15, 2011 - 9:14:40 PM
Last modification on : Thursday, July 1, 2021 - 5:58:07 PM
Long-term archiving on: : Friday, December 16, 2011 - 2:30:37 AM

Files

mairal11a.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00584817, version 3
  • ARXIV : 1104.1872

Collections

Citation

Julien Mairal, Rodolphe Jenatton, Guillaume Obozinski, Francis Bach. Convex and Network Flow Optimization for Structured Sparsity. Journal of Machine Learning Research, Microtome Publishing, 2011, 12, pp.2681−2720. ⟨inria-00584817v3⟩

Share

Metrics

Record views

782

Files downloads

910