vix.ing · top · new · best · stats · spec

DARTS: Differentiable Architecture Search

2018/06/24 by Hanxiao Liu, Karen Simonyan, Liu, Hanxiao +3 · 255 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Immunology and Microbiology · #Machine Learning in Bioinformatics #Multimodal Machine Learning Applications #interferon and immune responses

paper · pdf · doi:10.48550/arxiv.1806.09055

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.

Cited by

Related