Parametric Maxflows for Structured Sparse Learning with Convex Relaxations of Submodular Functions

The proximal problem for structured penalties obtained via convex relaxations of submodular functions is known to be equivalent to minimizing separable convex functions over the corresponding submodular polyhedra. In this paper, we reveal a comprehensive class of structured penalties for which penal...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Kawahara, Yoshinobu, Yamaguchi, Yutaro
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 14.09.2015
Subjects
Algorithms
Machine learning
Optimization
Online AccessGet full text

Cover

More Information
Summary:The proximal problem for structured penalties obtained via convex relaxations of submodular functions is known to be equivalent to minimizing separable convex functions over the corresponding submodular polyhedra. In this paper, we reveal a comprehensive class of structured penalties for which penalties this problem can be solved via an efficiently solvable class of parametric maxflow optimization. We then show that the parametric maxflow algorithm proposed by Gallo et al. and its variants, which runs, in the worst-case, at the cost of only a constant factor of a single computation of the corresponding maxflow optimization, can be adapted to solve the proximal problems for those penalties. Several existing structured penalties satisfy these conditions; thus, regularized learning with these penalties is solvable quickly using the parametric maxflow algorithm. We also investigate the empirical runtime performance of the proposed framework.
ISSN:2331-8422