Efficient Search of Multiple Neural Architectures with Different Complexities via Importance Sampling. (arXiv:2207.10334v1 [cs.NE])

Neural architecture search (NAS) aims to automate architecture design
processes and improve the performance of deep neural networks. Platform-aware
NAS methods consider both performance and complexity and can find
well-performing architectures with low computational resources. Although
ordinary NAS methods result in tremendous computational costs owing to the
repetition of model training, one-shot NAS, which trains the weights of a
supernetwork containing all candidate architectures only once during the search
process, has been reported to result in a lower search cost. …

arxiv importance neural architectures sampling search