BriefGPT.xyz
Apr, 2023
PED-ANOVA: 在任意子空间中高效量化超参数重要性
PED-ANOVA: Efficiently Quantifying Hyperparameter Importance in Arbitrary Subspaces
HTML
PDF
Shuhei Watanabe, Archit Bansal, Frank Hutter
TL;DR
本文提出了一种名为PED-ANOVA的算法，使用Pearson散度对不同子空间进行了贡献计算，以识别重要的Hyperparameter Optimization参数。
Abstract
The recent rise in popularity of
hyperparameter optimization
(HPO) for
deep learning
has highlighted the role that good hyperparameter (HP) space design can play in training strong models. In turn, designing a go
→