Papers › SNAS: Stochastic Neural Architecture Search
SNAS: Stochastic Neural Architecture Search
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 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
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