This website requires JavaScript.

A weak tail-bound probabilistic condition for function estimation in stochastic derivative-free optimization

Francesco RinaldiLuis Nunes VicenteDamiano Zeffiro
摘要
In this paper, we use tail bounds to define a tailored probabilisticcondition for function estimation that eases the theoretical analysis ofstochastic derivative-free optimization methods. In particular, we focus on theunconstrained minimization of a potentially non-smooth function, whose valuescan only be estimated via stochastic observations, and give a simplifiedconvergence proof for both a direct search and a basic trust-region scheme.
展开全部
图表提取

暂无人提供速读十问回答

论文十问由沈向洋博士提出,鼓励大家带着这十个问题去阅读论文,用有用的信息构建认知模型。写出自己的十问回答,还有机会在当前页面展示哦。

Q1论文试图解决什么问题?
Q2这是否是一个新的问题?
Q3这篇文章要验证一个什么科学假设?
0
被引用
笔记
问答