# EPNAS: Efficient Progressive Neural Architecture Search

Source: [EPNAS: Efficient Progressive Neural Architecture Search](<https://www.sota2.com/research/paper/68fa65fa1e209131cea0da56>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:40:30.056Z

Authors: Yanqi Zhou, Peng Wang, Sercan Arik, Haonan Yu, Syed Zawad, Feng Yan, Greg Diamos

Published: 2019-07-07T03:50:42.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1907.04648>)

[PDF](<https://arxiv.org/pdf/1907.04648.pdf>)