BriefGPT.xyz
Feb, 2017
带有置信上界的Frank-Wolfe算法在赌博优化中的快速变化率
Bandit Optimization with Upper-Confidence Frank-Wolfe
HTML
PDF
Quentin Berthet, Vianney Perchet
TL;DR
在这篇研究论文中，研究了一类被称为Bandit Optimization的问题，针对该问题，采用了基于Upper-Confidence Frank-Wolfe算法的一种新的优化方法，并提出了理论保证。
Abstract
We consider the problem of
bandit optimization
, inspired by stochastic optimization and
online learning
problems with bandit feedback. In this problem, the objective is to minimize a global loss function of all t
→