arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1402.2667cs.LGstat.ML
收藏

基于随机游动的零阶随机凸优化

On Zeroth-Order Stochastic Convex Optimization via Random Walks

The Wharton School, University of Pennsylvania(宾夕法尼亚大学沃顿商学院);University of Washington(华盛顿大学)

Tengyuan Liang, Hariharan Narayanan, Alexander Rakhlin

摘要:

我们提出了一种零阶随机凸优化方法,该方法在对凸有界函数$f:{\mathbb R}^n\to{\mathbb R}$进行$T$查询后,获得了$\tilde{\mathcal{O}}(n^{7}T^{-1/2})$的次优率。该方法是基于随机游走(\emph{Ball Walk})的epigraph的功能。随机化方法规避了梯度估计的问题,并且与无噪声零阶方法相比,对噪声函数评估似乎不太敏感。

英文摘要:

We propose a method for zeroth order stochastic convex optimization that attains the suboptimality rate of $\tilde{\mathcal{O}}(n^{7}T^{-1/2})$ after $T$ queries for a convex bounded function $f:{\mathbb R}^n\to{\mathbb R}$. The method is based on a random walk (the \emph{Ball Walk}) on the epigraph of the function. The randomized approach circumvents the problem of gradient estimation, and appears to be less sensitive to noisy function evaluations compared to noiseless zeroth order methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑