Best Practices for Scientific Research on Neural Architecture Search
- authored by
- Marius Lindauer, Frank Hutter
- Abstract
Finding a well-performing architecture is often tedious for both deep learning practitioners and researchers, leading to tremendous interest in the automation of this task by means of neural architecture search (NAS). Although the community has made major strides in developing better NAS methods, the quality of scientific empirical evaluations in the young field of NAS is still lacking behind that of other areas of machine learning. To address this issue, we describe a set of possible issues and ways to avoid them, leading to the NAS best practices checklist available at automl.org/nas_checklist.pdf.
- Organisation(s)
-
Machine Learning Section
Institute of Information Processing
- External Organisation(s)
-
University of Freiburg
- Type
- Article
- Journal
- Journal of Machine Learning Research
- Volume
- 21
- No. of pages
- 18
- ISSN
- 1532-4435
- Publication date
- 11.2020
- Publication status
- Published
- Peer reviewed
- Yes
- ASJC Scopus subject areas
- Software, Artificial Intelligence, Control and Systems Engineering, Statistics and Probability
- Electronic version(s)
-
https://arxiv.org/abs/1909.02453 (Access:
Open)
https://jmlr.csail.mit.edu/papers/volume21/20-056/20-056.pdf (Access: Open)
