NeurIPS 2020spotlight95 citations
A Study on Encodings for Neural Architecture Search
Colin White, Willie Neiswanger, Sam Nolen, Yash Savani
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.
BibTeX
@inproceedings{NEURIPS2020_ea4eb493,
author = {White, Colin and Neiswanger, Willie and Nolen, Sam and Savani, Yash},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin},
pages = {20309--20319},
publisher = {Curran Associates, Inc.},
title = {A Study on Encodings for Neural Architecture Search},
url = {https://proceedings.neurips.cc/paper_files/paper/2020/file/ea4eb49329550caaa1d2044105223721-Paper.pdf},
volume = {33},
year = {2020}
}