Understanding and Accelerating Neural Architecture Search With Training-Free and Theory-Grounded Metrics-Reference-Cited by-同舟云学术

Understanding and Accelerating Neural Architecture Search With Training-Free and Theory-Grounded Metrics

Author:

Chen Wuyang¹^ORCID,Gong Xinyu¹^ORCID,Wu Junru²^ORCID,Wei Yunchao³^ORCID,Shi Humphrey⁴^ORCID,Yan Zhicheng⁵^ORCID,Yang Yi⁶^ORCID,Wang Zhangyang¹^ORCID

Affiliation:

1. Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA

2. Department of Computer Science and Engineering, Texas A&M University, College Station, TX, USA

3. Institute of Information Science, Beijing Jiaotong University, Beijing, China

4. School of Interactive Computing, Georgia Institute of Technology, Atlanta, GA, USA

5. Meta Reality Labs, Burlingame, CA, USA

6. Zhejiang University, Hangzhou, China

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Applied Mathematics,Artificial Intelligence,Computational Theory and Mathematics,Computer Vision and Pattern Recognition,Software

Link

Reference98 articles.

1. Neural architecture search without training;Mellor

2. Neural architecture search on imagenet in four GPU hours: A theoretically inspired perspective;Chen

3. Zero-cost proxies for lightweight NAS;Abdelfattah

4. Very deep convolutional networks for large-scale image recognition;Simonyan,2014

Cited by 1 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献