Best Practices for Scientific Research on Neural Architecture Search
This work aims to enhance the reliability and reproducibility of NAS research for the machine learning community, though it is incremental as it builds on existing concerns without introducing new methods.
The paper addresses the lack of rigorous empirical evaluations in neural architecture search (NAS) by proposing a checklist of best practices to improve research quality.
Finding a well-performing architecture is often tedious for both DL 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 http://automl.org/nas_checklist.pdf.