Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap

Xin Chen
Xin Chen
Kaifeng Bi
Kaifeng Bi
Yuhui Xu
Yuhui Xu
Zhengsu Chen
Zhengsu Chen
Lanfei Wang
Lanfei Wang
An Xiao
An Xiao
Jianlong Chang
Jianlong Chang
Xiaopeng Zhang
Xiaopeng Zhang
Cited by: 0|Bibtex|Views19|Links

Abstract:

Neural architecture search (NAS) has attracted increasing attentions in both academia and industry. In the early age, researchers mostly applied individual search methods which sample and evaluate the candidate architectures separately and thus incur heavy computational overheads. To alleviate the burden, weight-sharing methods were pro...More

Code:

Data:

Your rating :
0

 

Tags
Comments