Mutation Is All You Need
Abstract
Neural architecture search (NAS) promises to make deep learning accessible to non-experts by automating architecture engineering of deep neural networks. BANANAS is one state-of-the-art NAS method that is embedded within the Bayesian optimization framework. Recent experimental findings have demonstrated the strong performance of BANANAS on the NAS-Bench-101 benchmark being determined by its path encoding and not its choice of surrogate model. We present experimental results suggesting that the performance of BANANAS on the NAS-Bench-301 benchmark is determined by its acquisition function optimizer, which minimally mutates the incumbent.
Cite
Text
Schneider et al. "Mutation Is All You Need." ICML 2021 Workshops: AutoML, 2021.Markdown
[Schneider et al. "Mutation Is All You Need." ICML 2021 Workshops: AutoML, 2021.](https://mlanthology.org/icmlw/2021/schneider2021icmlw-mutation/)BibTeX
@inproceedings{schneider2021icmlw-mutation,
title = {{Mutation Is All You Need}},
author = {Schneider, Lennart and Pfisterer, Florian and Binder, Martin and Bischl, Bernd},
booktitle = {ICML 2021 Workshops: AutoML},
year = {2021},
url = {https://mlanthology.org/icmlw/2021/schneider2021icmlw-mutation/}
}