Abstract

The time and effort involved in hand-designing deep neural networks is immense. This has prompted the development of Neural Architecture Search (NAS) techniques to automate this design. However, NAS algorithms tend to be slow and expensive; they need to train vast numbers of candidate networks to inform the search process. This could be alleviated if we could partially predict a network’s trained accuracy from its initial state. In this work, we examine the overlap of activations between datapoints in untrained networks and motivate how this can give a measure which is usefully indicative of a network’s trained performance. We incorporate this measure into a simple algorithm that allows us to search for powerful networks without any training in a matter of seconds on a single GPU, and verify its effectiveness on NAS-Bench-101, NASBench-201, NATS-Bench, and Network Design Spaces. Our approach can be readily combined with more expensive search methods; we examine a simple adaptation of regularised evolutionary search. Code for reproducing our experiments is available at https://github.com/BayesWatch/nas-without-training.
Original languageEnglish
DOIs
Publication statusPublished - 18 Jul 2021
EventThirty-eighth International Conference on Machine Learning - Online
Duration: 18 Jul 202124 Jul 2021
https://icml.cc/

Conference

ConferenceThirty-eighth International Conference on Machine Learning
Abbreviated titleICML 2021
Period18/07/2124/07/21
Internet address

Fingerprint

Dive into the research topics of 'Neural Architecture Search without Training'. Together they form a unique fingerprint.

Cite this