Provable Submodular Minimization using Wolfe's Algorithm

Abstract

Owing to several applications in large scale learning and vision problems, fast submodular function minimization (SFM) has become a critical problem. Theoretically, unconstrained SFM can be performed in polynomial time [IFF 2001, IO 2009]. However, these algorithms are typically not practical. In 1976, Wolfe proposed an algorithm to find the minimum Euclidean norm point in a polytope, and in 1980, Fujishige showed how Wolfe's algorithm can be used for SFM. For general submodular functions, this Fujishige-Wolfe minimum norm algorithm seems to have the best empirical performance. Despite its good practical performance, very little is known about Wolfe's minimum norm algorithm theoretically. To our knowledge, the only result is an exponential time analysis due to Wolfe himself. In this paper we give a maiden convergence analysis of Wolfe's algorithm. We prove that in $t$ iterations, Wolfe's algorithm returns an $O(1/t)$-approximate solution to the min-norm point on {\em any} polytope. We also prove a robust version of Fujishige's theorem which shows that an $O(1/n^2)$-approximate solution to the min-norm point on the base polytope implies {\em exact} submodular minimization. As a corollary, we get the first pseudo-polynomial time guarantee for the Fujishige-Wolfe minimum norm algorithm for unconstrained submodular function minimization.

References in corpus (3)

• Submodular Optimization with Submodular Cover and Submodular Knapsack Constraints
• Efficient Minimization of Decomposable Submodular Functions
• Convex Analysis and Optimization with Submodular Functions: a Tutorial

Cited by in corpus (8)

• Scalable Variational Inference in Log-supermodular Models
• A totally unimodular view of structured sparsity
• Revisiting Decomposable Submodular Function Minimization with Incidence Relations
• On a reduction for a class of resource allocation problems
• Fast Decomposable Submodular Function Minimization using Constrained Total Variation
• Quadratic Decomposable Submodular Function Minimization: Theory and Practice (Computation and Analysis of PageRank over Hypergraphs)
• A Policy Efficient Reduction Approach to Convex Constrained Deep Reinforcement Learning
• Control of Generalized Discrete-time SIS Epidemics via Submodular Function Minimization