Semantic Scholar Open Access 2018 4852 sitasi

DARTS: Differentiable Architecture Search

Hanxiao Liu K. Simonyan Yiming Yang

Abstrak

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. Our implementation has been made publicly available to facilitate further research on efficient architecture search algorithms.

Penulis (3)

H

Hanxiao Liu

K

K. Simonyan

Y

Yiming Yang

Format Sitasi

Liu, H., Simonyan, K., Yang, Y. (2018). DARTS: Differentiable Architecture Search. https://www.semanticscholar.org/paper/c1f457e31b611da727f9aef76c283a18157dfa83

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →
Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2018
Bahasa
en
Total Sitasi
4852×
Sumber Database
Semantic Scholar
Akses
Open Access ✓