Decomposable Submodular Function Minimization: Discrete and Continuous

Abstract

This paper investigates connections between discrete and continuous approaches for decomposable submodular function minimization. We provide improved running time estimates for the state-of-the-art continuous algorithms for the problem using combinatorial arguments. We also provide a systematic experimental comparison of the two types of methods, based on a clear distinction between level-0 and level-1 algorithms.

Cited by in corpus (2)

• Structured Optimal Transport
• Fast Decomposable Submodular Function Minimization using Constrained Total Variation