Majorisation-minimisation algorithms for minimising the difference between lattice submodular functions

Abstract

We consider the problem of minimising functions represented as a difference of lattice submodular functions. We propose analogues to the SupSub, SubSup and ModMod routines for lattice submodular functions. We show that our majorisation-minimisation algorithms produce iterates that monotonically decrease, and that we converge to a local minimum. We also extend additive hardness results, and show that a broad range of functions can be expressed as the difference of submodular functions.

13 pages

References in corpus (3)

• Non-monotone submodular maximization under matroid and knapsack constraints
• Learning Mixtures of Submodular Shells with Application to Document Summarization
• A submodular-supermodular procedure with applications to discriminative structure learning