Poster
DARTS: Differentiable Architecture Search
Hanxiao Liu · Karen Simonyan · Yiming Yang
Great Hall BC #71
Keywords: [ deep learning ] [ image classification ] [ language modeling ] [ neural architecture search ] [ automl ]
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.
Live content is unavailable. Log in and register to view live content