Recently Neural Architecture Search (NAS) has aroused great interest in both
academia and industry, however it remains challenging because of its huge and
non-continuous search space. Instead of applying evolutionary algorithm or
reinforcement learning as previous works, this paper proposes a Direct Sparse
Optimization NAS (DSO-NAS) method. In DSO-NAS, we provide a novel model pruning
view to NAS problem. In specific, we start from a completely connected block,
and then introduce scaling factors to scale the information flow between
operations. Next, we impose sparse regularizations to prune useless connections
in the architecture. Lastly, we derive an efficient and theoretically sound
optimization method to solve it. Our method enjoys both advantages of
differentiability and efficiency, therefore can be directly applied to large
datasets like ImageNet. Particularly, On CIFAR-10 dataset, DSO-NAS achieves an
average test error 2.84\%, while on the ImageNet dataset DSO-NAS achieves
25.4\% test error under 600M FLOPs with 8 GPUs in 18 hours.
%0 Generic
%1 citeulike:14663225
%A xxx,
%D 2018
%K arch backbone classification nas
%T You Only Search Once: Single Shot Neural Architecture Search via Direct Sparse Optimization
%U http://arxiv.org/abs/1811.01567
%X Recently Neural Architecture Search (NAS) has aroused great interest in both
academia and industry, however it remains challenging because of its huge and
non-continuous search space. Instead of applying evolutionary algorithm or
reinforcement learning as previous works, this paper proposes a Direct Sparse
Optimization NAS (DSO-NAS) method. In DSO-NAS, we provide a novel model pruning
view to NAS problem. In specific, we start from a completely connected block,
and then introduce scaling factors to scale the information flow between
operations. Next, we impose sparse regularizations to prune useless connections
in the architecture. Lastly, we derive an efficient and theoretically sound
optimization method to solve it. Our method enjoys both advantages of
differentiability and efficiency, therefore can be directly applied to large
datasets like ImageNet. Particularly, On CIFAR-10 dataset, DSO-NAS achieves an
average test error 2.84\%, while on the ImageNet dataset DSO-NAS achieves
25.4\% test error under 600M FLOPs with 8 GPUs in 18 hours.
@misc{citeulike:14663225,
abstract = {{ Recently Neural Architecture Search (NAS) has aroused great interest in both
academia and industry, however it remains challenging because of its huge and
non-continuous search space. Instead of applying evolutionary algorithm or
reinforcement learning as previous works, this paper proposes a Direct Sparse
Optimization NAS (DSO-NAS) method. In DSO-NAS, we provide a novel model pruning
view to NAS problem. In specific, we start from a completely connected block,
and then introduce scaling factors to scale the information flow between
operations. Next, we impose sparse regularizations to prune useless connections
in the architecture. Lastly, we derive an efficient and theoretically sound
optimization method to solve it. Our method enjoys both advantages of
differentiability and efficiency, therefore can be directly applied to large
datasets like ImageNet. Particularly, On CIFAR-10 dataset, DSO-NAS achieves an
average test error 2.84\%, while on the ImageNet dataset DSO-NAS achieves
25.4\% test error under 600M FLOPs with 8 GPUs in 18 hours.}},
added-at = {2019-02-27T22:23:29.000+0100},
archiveprefix = {arXiv},
author = {xxx},
biburl = {https://www.bibsonomy.org/bibtex/234ab901e03b3f3ede096f8096acb6ae1/nmatsuk},
citeulike-article-id = {14663225},
citeulike-linkout-0 = {http://arxiv.org/abs/1811.01567},
citeulike-linkout-1 = {http://arxiv.org/pdf/1811.01567},
day = 5,
eprint = {1811.01567},
interhash = {7dd3df699d6248756957a7a55acb6486},
intrahash = {34ab901e03b3f3ede096f8096acb6ae1},
keywords = {arch backbone classification nas},
month = nov,
posted-at = {2018-12-13 08:02:51},
priority = {5},
timestamp = {2019-02-27T22:23:29.000+0100},
title = {{You Only Search Once: Single Shot Neural Architecture Search via Direct Sparse Optimization}},
url = {http://arxiv.org/abs/1811.01567},
year = 2018
}