Neural Architecture Search (NAS) is an exciting new field of study that is taking representation learning to the next level by allowing us to learn the architectures in a data-driven way that then enables efficient learning of representations. While representation learning removed the need of manual feature engineering, it shifted the manual task to the manual selection of architectures; as a natural next step, NAS replaces this manual architecture selection step, allowing us true end-to-end learning of the architecture, the features, and the final classifier using the features expressed as instantiations of the architecture.

Since the first workshop on NAS at ICLR 2020, there have been many new developments in NAS. Firstly, there has been a large increase in standardized tabular benchmarks and more researchers releasing source code, leading to more rigorous empirical NAS research and also allowing research groups without access to industry-scale compute resources to run thorough experimental evaluations. Secondly, there are now several works aiming for standardized and modularized open-source libraries that allow for both clean evaluations of different approaches without confounding factors and for mixing and matching components of different NAS methods. Finally, by now there are also several applications of NAS beyond its original narrow focus on object recognition, to fields like semantic segmentation, speech recognition, and natural language processing.

In this workshop, we want to push NAS to the next level and aim to address questions (see proposal) which are of particular relevance to the NAS community. In terms of prospective participants, our main targets are machine learning researchers interested in understanding and improving current NAS methods, but ML researchers planning to apply existing NAS methods to novel domains are also amongst the target community.