BriefGPT.xyz
Feb, 2018
分布鲁棒子模最大化
Distributionally Robust Submodular Maximization
HTML
PDF
Matthew Staib, Bryan Wilder, Stefanie Jegelka
TL;DR
通过直接优化偏差和方差的组合，该研究通过展示如何进行具有理论保证的高效算法，从而在次模函数中进行分布式鲁棒优化（DRO），从而实现在未知随机次模函数的情况下实现更好的性能和更好的推广。
Abstract
submodular functions
have applications throughout machine learning, but in many settings, we do not have direct access to the underlying function $f$. We focus on
stochastic functions
that are given as an expecta
→