UAI 2019poster897 citations

Random Search and Reproducibility for Neural Architecture Search

Liam Li, Ameet Talwalkar

Abstract

Neural architecture search (NAS) is a promising research direction that has the potential to replace expert-designed networks with learned, task-specific architectures. In order to help ground the empirical results in this field, we propose new NAS baselines that build off the following observations: (i) NAS is a specialized hyperparameter optimization problem; and (ii) random search is a competitive baseline for hyperparameter optimization. Leveraging these observations, we evaluate both random search with early-stopping and a novel random search with weight-sharing algorithm on two standard NAS benchmarks—PTB and CIFAR-10. Our results show that random search with early-stopping is a competitive NAS baseline, e.g., it performs at least as well as ENAS, a leading NAS method, on both benchmarks. Additionally, random search with weight-sharing outperforms random search with early-stopping, achieving a state-of-the-art NAS result on PTB and a highly competitive result on CIFAR-10. Finally, we explore the existing reproducibility issues of published NAS results.

BibTeX
@InProceedings{pmlr-v115-li20c,
  title = 	 {Random Search and Reproducibility for Neural Architecture Search},
  author =       {Li, Liam and Talwalkar, Ameet},
  booktitle = 	 {Proceedings of The 35th Uncertainty in Artificial Intelligence Conference},
  pages = 	 {367--377},
  year = 	 {2020},
  editor = 	 {Adams, Ryan P. and Gogate, Vibhav},
  volume = 	 {115},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {22--25 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v115/li20c/li20c.pdf},
  url = 	 {https://proceedings.mlr.press/v115/li20c.html},
  abstract = 	 {Neural architecture search (NAS) is a promising research direction that has the potential to replace expert-designed networks with learned, task-specific architectures. In order to help ground the empirical results in this field, we propose new NAS baselines that build off the following observations: (i) NAS is a specialized hyperparameter optimization problem; and (ii) random search is a competitive baseline for hyperparameter optimization. Leveraging these observations, we evaluate both random search with early-stopping and a novel random search with weight-sharing algorithm on two standard NAS benchmarks—PTB and CIFAR-10. Our results show that random search with early-stopping is a competitive NAS baseline, e.g., it performs at least as well as ENAS, a leading NAS method, on both benchmarks. Additionally, random search with weight-sharing outperforms random search with early-stopping, achieving a state-of-the-art NAS result on PTB and a highly competitive result on CIFAR-10. Finally, we explore the existing reproducibility issues of published NAS results.}
}
Random Search and Reproducibility for Neural Architecture Search · UAI 2019