BriefGPT.xyz
May, 2016
水平可扩展次模最大化
Horizontally Scalable Submodular Maximization
HTML
PDF
Mario Lucic, Olivier Bachem, Morteza Zadimoghaddam, Andreas Krause
TL;DR
该篇论文提出了一种针对固定容量的分布式子模型最大化的框架,应用于广泛的算法和约束条件,并且为任何可用容量提供近似因子的理论保证,并在多个数据集上进行了实证评估,表现竞争性与中心化贪婪算法相当。
Abstract
A variety of
large-scale machine learning
problems can be cast as instances of constrained submodular maximization. Existing approaches for
distributed submodular maximization
have a critical drawback: The capaci
→