arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1808.09830cs.LGstat.ML
收藏

寻找Pareto最优的设备感知神经结构

Searching Toward Pareto-Optimal Device-Aware Neural Architectures

National Tsing-Hua University(国立清华大学);Google Research(谷歌研究院)

An-Chieh Cheng, Jin-Dong Dong, Chi-Hung Hsu, Shu-Huan Chang, Min Sun, Shih-Chieh Chang, Jia-Yu Pan, Yu-Ting Chen, Wei Wei, Da-Cheng Juan

摘要:

神经架构搜索(NAS)的最新突破在图像分类和语言理解等许多任务中实现了最先进的性能。然而,大多数现有的工作只优化模型的准确性,并在很大程度上忽略了其他重要的因素所施加的底层硬件和设备,如延迟和能源,当进行推理。在本文中,我们首先介绍了NAS的问题,并提供了一个调查最近的工作。然后,我们深入研究了最近将NAS扩展到多目标框架的两个进展:MONAS和DPP-Net。MONAS和DPP-Net都能够优化设备的准确性和其他目标,搜索可以最好地部署在各种设备上的神经架构:从嵌入式系统和移动设备到工作站。实验结果表明,MONAS和DPP-Net发现的架构实现了帕累托最优性,对于各种设备的给定目标。

英文摘要:

Recent breakthroughs in Neural Architectural Search (NAS) have achieved state-of-the-art performance in many tasks such as image classification and language understanding. However, most existing works only optimize for model accuracy and largely ignore other important factors imposed by the underlying hardware and devices, such as latency and energy, when making inference. In this paper, we first introduce the problem of NAS and provide a survey on recent works. Then we deep dive into two recent advancements on extending NAS into multiple-objective frameworks: MONAS and DPP-Net. Both MONAS and DPP-Net are capable of optimizing accuracy and other objectives imposed by devices, searching for neural architectures that can be best deployed on a wide spectrum of devices: from embedded systems and mobile devices to workstations. Experimental results are poised to show that architectures found by MONAS and DPP-Net achieves Pareto optimality w.r.t the given objectives for various devices.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑