Papers › SNAS: Stochastic Neural Architecture Search

SNAS: Stochastic Neural Architecture Search

24 Dec 2018ICLR 2019 5arXiv:1812.09926archive 2025-07-28

Sirui Xie, Hehui Zheng, Chunxiao Liu, Liang Lin

We propose Stochastic Neural Architecture Search (SNAS), an economical end-to-end solution to Neural Architecture Search (NAS) that trains neural operation parameters and architecture distribution parameters in same round of back-propagation, while maintaining the completeness and differentiability of the NAS pipeline. In this work, NAS is reformulated as an optimization problem on parameters of a joint distribution for the search space in a cell. To leverage the gradient information in generic differentiable loss for architecture search, a novel search gradient is proposed. We prove that this search gradient optimizes the same objective as reinforcement-learning-based NAS, but assigns credits to structural decisions more efficiently. This credit assignment is further augmented with locally decomposable reward to enforce a resource-efficient constraint. In experiments on CIFAR-10, SNAS takes less epochs to find a cell architecture with state-of-the-art accuracy than non-differentiable evolution-based and reinforcement-learning-based NAS, which is also transferable to ImageNet. It is also shown that child networks of SNAS can maintain the validation accuracy in searching, with which attention-based NAS requires parameter retraining to compete, exhibiting potentials to stride towards efficient NAS on big datasets. We have released our implementation at https://github.com/SNAS-Series/SNAS-Series.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

SNAS-Series/SNAS-Series officialmentioned in papermentioned on GitHubpytorchMIT report
JunrQ/NAS mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Neural Architecture SearchReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Neural Architecture Search NAS-Bench-201, CIFAR-10 SNAS Accuracy (Test) 92.77 #27 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-10 SNAS Accuracy (Val) 90.10 #27 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-100 SNAS Accuracy (Test) 69.34 #30 of 40 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-100 SNAS Accuracy (Val) 69.69 #30 of 40 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 SNAS Accuracy (Test) 43.16 #31 of 49 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

LSTMSigmoid ActivationSoftmaxTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections