DARTS: Differentiable Architecture Search

Abstract

This paper addresses the scalability challenge of architecture search by formulating the task in a differentiable manner. Unlike conventional approaches of applying evolution or reinforcement learning over a discrete and non-differentiable search space, our method is based on the continuous relaxation of the architecture representation, allowing efficient search of the architecture using gradient descent. Extensive experiments on CIFAR-10, ImageNet, Penn Treebank and WikiText-2 show that our algorithm excels in discovering high-performance convolutional architectures for image classification and recurrent architectures for language modeling, while being orders of magnitude faster than state-of-the-art non-differentiable techniques.

Cite

Text

Liu et al. "DARTS: Differentiable Architecture Search." International Conference on Learning Representations, 2019.

Markdown

[Liu et al. "DARTS: Differentiable Architecture Search." International Conference on Learning Representations, 2019.](https://mlanthology.org/iclr/2019/liu2019iclr-darts/)

BibTeX

@inproceedings{liu2019iclr-darts,
  title     = {{DARTS: Differentiable Architecture Search}},
  author    = {Liu, Hanxiao and Simonyan, Karen and Yang, Yiming},
  booktitle = {International Conference on Learning Representations},
  year      = {2019},
  url       = {https://mlanthology.org/iclr/2019/liu2019iclr-darts/}
}