BriefGPT.xyz
Apr, 2016
使用CMA-ES算法对深度神经网络的超参数进行优化
CMA-ES for Hyperparameter Optimization of Deep Neural Networks
HTML
PDF
Ilya Loshchilov, Frank Hutter
TL;DR
本文提出使用CMA-ES算法作为深度神经网络超参数优化的一种可行的选择，通过一个MNIST数据集的卷积神经网络的toy experiment，对比了CMA-ES和Bayesian优化算法在30个GPU并行计算下的效果。
Abstract
Hyperparameters of
deep neural networks
are often optimized by grid search, random search or Bayesian optimization. As an alternative, we propose to use the
covariance matrix adaptation evolution strategy
(CMA-ES
→