EPNAS: Efficient Progressive Neural Architecture Search
This work addresses the need for scalable and resource-constrained neural architecture search, crucial for deployment on platforms like mobile and cloud, but it is incremental as it builds on existing NAS approaches.
The paper tackles the problem of efficiently searching neural architectures in large spaces by proposing EPNAS, a progressive search method with performance prediction, which achieves superior speed and accuracy on CIFAR10 and ImageNet compared to state-of-the-art methods.
In this paper, we propose Efficient Progressive Neural Architecture Search (EPNAS), a neural architecture search (NAS) that efficiently handles large search space through a novel progressive search policy with performance prediction based on REINFORCE~\cite{Williams.1992.PG}. EPNAS is designed to search target networks in parallel, which is more scalable on parallel systems such as GPU/TPU clusters. More importantly, EPNAS can be generalized to architecture search with multiple resource constraints, \eg, model size, compute complexity or intensity, which is crucial for deployment in widespread platforms such as mobile and cloud. We compare EPNAS against other state-of-the-art (SoTA) network architectures (\eg, MobileNetV2~\cite{mobilenetv2}) and efficient NAS algorithms (\eg, ENAS~\cite{pham2018efficient}, and PNAS~\cite{Liu2017b}) on image recognition tasks using CIFAR10 and ImageNet. On both datasets, EPNAS is superior \wrt architecture searching speed and recognition accuracy.