Corpus ID: 219708698

Bonsai-Net: One-Shot Neural Architecture Search via Differentiable Pruners

@article{Geada2020BonsaiNetON,
  title={Bonsai-Net: One-Shot Neural Architecture Search via Differentiable Pruners},
  author={Rob Geada and Dennis Prangle and A. Stephen McGough},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.09264}
}
  • Rob Geada, Dennis Prangle, A. Stephen McGough
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • One-shot Neural Architecture Search (NAS) aims to minimize the computational expense of discovering state-ofthe-art models. However, in the past year attention has been drawn to the comparable performance of naı̈ve random search across the same search spaces used by leading NAS algorithms. To address this, we explore the effects of drastically relaxing the NAS search space, and we present Bonsai-Net 1, an efficient one-shot NAS method to explore our relaxed search space. Bonsai-Net is built… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    References

    Publications referenced by this paper.
    SHOWING 1-7 OF 7 REFERENCES

    DARTS: differentiable architecture

    • Hanxiao Liu, Karen Simonyan, Yiming Yang
    • search. CoRR,
    • 2019
    VIEW 9 EXCERPTS
    HIGHLY INFLUENTIAL

    DARTS: differentiable architecture search. CoRR, abs/1806.09055

    • Hanxiao Liu, Karen Simonyan, Yiming Yang
    • 2019

    Deep Residual Learning for Image Recognition

    VIEW 2 EXCERPTS