NeurIPS 2020

A Study on Encodings for Neural Architecture Search

Meta Review

This paper thoroughly studies both the empirical and theoretical aspects of what encodings to use for representing architectures for the task of predicting their downstream final performance. This step is fundamental to many NAS pipelines. This is a fundamental contribution to NAS literature and should become the go-to paper to read for others trying to design their own NAS pipeline. The authors are encouraged to incorporate all reviewer comments to further improve their paper.