Progressive Neural Architecture Search

Chenxi Liu, Barret Zoph, Maxim Neumann, Jonathon Shlens, Wei Hua, Li-Jia Li, Li Fei-Fei, Alan Yuille, Jonathan Huang, Kevin Murphy

ECCV 2018

doi:10.1007/978-3-030-01246-5_2 /eccv/2018/liu2018eccv-progressive/

Abstract

We propose a new method for learning the structure of convolutional neural networks (CNNs) that is more efficient than recent state-of-the-art methods based on reinforcement learning and evolutionary algorithms. Our approach uses a sequential model-based optimization (SMBO) strategy, in which we search for structures in order of increasing complexity, while simultaneously learning a surrogate model to guide the search through structure space. Direct comparison under the same search space shows that our method is up to 5 times more efficient than the RL method of Zoph et al. (2018) in terms of number of models evaluated, and 8 times faster in terms of total compute. The structures we discover in this way achieve state of the art classification accuracies on CIFAR-10 and ImageNet.

PDF ECCV Semantic Scholar

Cite

Text

Liu et al. "Progressive Neural Architecture Search." Proceedings of the European Conference on Computer Vision (ECCV), 2018. doi:10.1007/978-3-030-01246-5_2

Markdown

[Liu et al. "Progressive Neural Architecture Search." Proceedings of the European Conference on Computer Vision (ECCV), 2018.](https://mlanthology.org/eccv/2018/liu2018eccv-progressive/) doi:10.1007/978-3-030-01246-5_2

BibTeX

@inproceedings{liu2018eccv-progressive,
  title     = {{Progressive Neural Architecture Search}},
  author    = {Liu, Chenxi and Zoph, Barret and Neumann, Maxim and Shlens, Jonathon and Hua, Wei and Li, Li-Jia and Fei-Fei, Li and Yuille, Alan and Huang, Jonathan and Murphy, Kevin},
  booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
  year      = {2018},
  doi       = {10.1007/978-3-030-01246-5_2},
  url       = {https://mlanthology.org/eccv/2018/liu2018eccv-progressive/}
}