Re:Darts: Differentiable architecture search for convolution...
by ashelmire on Friday July 13, 2018 @02:45PM
(#17525624)
Cool, was thinking about this subject earlier today.
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.
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.
Zoph's paper on architecture search: https://arxiv.org/abs/1611.01578
Concept of architecture search from ages ago: https://static1.squarespace.com/static/58e2a71bf7e0ab3ba886c...