A Study on Encodings for Neural Architecture Search
Abstract
Neural architecture search (NAS) has been extensively studied in the past few years. A popular approach is to represent each neural architecture in the search space as a directed acyclic graph (DAG), and then search over all DAGs by encoding the adjacency matrix and list of operations as a set of hyperparameters. Recent work has demonstrated that even small changes to the way each architecture is encoded can have a significant effect on the performance of NAS algorithms.
Cite
Text
White et al. "A Study on Encodings for Neural Architecture Search." Neural Information Processing Systems, 2020.Markdown
[White et al. "A Study on Encodings for Neural Architecture Search." Neural Information Processing Systems, 2020.](https://mlanthology.org/neurips/2020/white2020neurips-study/)BibTeX
@inproceedings{white2020neurips-study,
title = {{A Study on Encodings for Neural Architecture Search}},
author = {White, Colin and Neiswanger, Willie and Nolen, Sam and Savani, Yash},
booktitle = {Neural Information Processing Systems},
year = {2020},
url = {https://mlanthology.org/neurips/2020/white2020neurips-study/}
}