NeurIPS 2017Spotlight

Decomposable Submodular Function Minimization: Discrete and Continuous

作者: Alina Ene, Huy Nguyen, László A. Végh

摘要

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.

PDF打开原文