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.
@article{arxiv.2107.07343,
title = {Mutation is all you need},
author = {Lennart Schneider and Florian Pfisterer and Martin Binder and Bernd Bischl},
journal= {arXiv preprint arXiv:2107.07343},
year = {2021}
}
Comments
Accepted for the 8th ICML Workshop on Automated Machine Learning (2021). 10 pages, 1 table, 3 figures