LGCLCVMLJun 24, 2018

DARTS: Differentiable Architecture Search

arXiv:1806.09055v24944 citations
Originality Highly original
AI Analysis

This addresses the problem of inefficient architecture search for researchers and practitioners in machine learning, offering a scalable and faster alternative to existing methods.

The paper tackles the scalability challenge of architecture search by formulating it in a differentiable manner, achieving high-performance architectures for image classification and language modeling while being orders of magnitude faster than state-of-the-art non-differentiable techniques.

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.

Code Implementations59 repos

Data from Papers with Code (CC-BY-SA-4.0)

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes