Maximizing submodular functions using probabilistic graphical models - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year : 2013

Maximizing submodular functions using probabilistic graphical models


We consider the problem of maximizing submodular functions; while this problem is known to be NP-hard, several numerically efficient local search techniques with approximation guarantees are available. In this paper, we propose a novel convex relaxation which is based on the relationship between submodular functions, entropies and probabilistic graphical models. In a graphical model, the entropy of the joint distribution decomposes as a sum of marginal entropies of subsets of variables; moreover, for any distribution, the entropy of the closest distribution factorizing in the graphical model provides an bound on the entropy. For directed graphical models, this last property turns out to be a direct consequence of the submodularity of the entropy function, and allows the generalization of graphical-model-based upper bounds to any submodular functions. These upper bounds may then be jointly maximized with respect to a set, while minimized with respect to the graph, leading to a convex variational inference scheme for maximizing submodular functions, based on outer approximations of the marginal polytope and maximum likelihood bounded treewidth structures. By considering graphs of increasing treewidths, we may then explore the trade-off between computational complexity and tightness of the relaxation. We also present extensions to constrained problems and maximizing the difference of submodular functions, which include all possible set functions.
Fichier principal
Vignette du fichier
smgm.pdf (180.63 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00860575 , version 1 (10-09-2013)



K. S. Sesh Kumar, Francis Bach. Maximizing submodular functions using probabilistic graphical models. 2013. ⟨hal-00860575⟩
302 View
801 Download



Gmail Facebook X LinkedIn More