Neural Architecture Search via Two Constant Shared Weights Initialisations

arXiv:2302.04406v2 Announce Type: replace
Abstract: In recent years, zero-cost metrics are gaining ground in neural architecture search (NAS). There metrics allow finding the optimal neural network for a given task faster and with a lesser computational load than conventional NAS methods. Equally important is that they also shed some light on the internal workings of neural architectures. This paper presents a zero-cost metric that highly correlated with the train set accuracy across the NAS-Bench-101, NAS-Bench-201 and NAS-Bench-NLP benchmark datasets. We …

architecture arxiv cs.ai cs.lg neural architecture search search type via