Path-Level Network Transformation for Efficient Architecture Search

@inproceedings{Cai2018PathLevelNT,
  title={Path-Level Network Transformation for Efficient Architecture Search},
  author={Han Cai and Jiacheng Yang and Weinan Zhang and Song Han and Yong Yu},
  booktitle={ICML},
  year={2018}
}
We introduce a new function-preserving transformation for efficient neural architecture search. This network transformation allows reusing previously trained networks and existing successful architectures that improves sample efficiency. We aim to address the limitation of current network transformation operations that can only perform layer-level architecture modifications, such as adding (pruning) filters or inserting (removing) a layer, which fails to change the topology of connection paths… CONTINUE READING
Tweets
This paper has been referenced on Twitter 24 times. VIEW TWEETS