BriefGPT.xyz
Jun, 2019
黑盒函数的逐步优化
Graduated Optimization of Black-Box Functions
HTML
PDF
Weijia Shao, Christian Geißler, Fikret Sivrikaya
TL;DR
本论文提出了一种新的方法,利用估计梯度来逐渐自适应地优化机器学习中的未知函数,并验证了该方法在低维和高维问题上的实验性能,证明了在调整高维超参数时我们的方法的优越性。
Abstract
Motivated by the problem of tuning
hyperparameters
in
machine learning
, we present a new approach for gradually and adaptively optimizing an unknown function using
→