Decomposable Submodular Function Minimization: Discrete and Continuous
Machine Learning
2017-03-07 v1 Data Structures and Algorithms
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.
Cite
@article{arxiv.1703.01830,
title = {Decomposable Submodular Function Minimization: Discrete and Continuous},
author = {Alina Ene and Huy L. Nguyen and László A. Végh},
journal= {arXiv preprint arXiv:1703.01830},
year = {2017}
}