SOTAVerified

DARTS: Differentiable Architecture Search

2018-06-24ICLR 2019Code Available1· sign in to hype

Hanxiao Liu, Karen Simonyan, Yiming Yang

arXivPDF

Code Available — Be the first to reproduce this paper.

Reproduce

Code

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

Tasks

General Classificationimage-classificationImage ClassificationLanguage ModelingLanguage ModellingNeural Architecture Searchreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
Penn Treebank (Word Level)Differentiable NASTest perplexity56.1—Unverified

Reproductions