Papers › MSR-DARTS: Minimum Stable Rank of Differentiable Architecture Search

MSR-DARTS: Minimum Stable Rank of Differentiable Architecture Search

19 Sep 2020arXiv:2009.09209archive 2025-07-28

Kengo Machida, Kuniaki Uto, Koichi Shinoda, Taiji Suzuki

In neural architecture search (NAS), differentiable architecture search (DARTS) has recently attracted much attention due to its high efficiency. It defines an over-parameterized network with mixed edges, each of which represents all operator candidates, and jointly optimizes the weights of the network and its architecture in an alternating manner. However, this method finds a model with the weights converging faster than the others, and such a model with fastest convergence often leads to overfitting. Accordingly, the resulting model cannot always be well-generalized. To overcome this problem, we propose a method called minimum stable rank DARTS (MSR-DARTS), for finding a model with the best generalization error by replacing architecture optimization with the selection process using the minimum stable rank criterion. Specifically, a convolution operator is represented by a matrix, and MSR-DARTS selects the one with the smallest stable rank. We evaluated MSR-DARTS on CIFAR-10 and ImageNet datasets. It achieves an error rate of 2.54% with 4.0M parameters within 0.3 GPU-days on CIFAR-10, and a top-1 error rate of 23.9% on ImageNet. The official code is available at https://github.com/mtaecchhi/msrdarts.git.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Neural Architecture Search

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Neural Architecture Search CIFAR-10 MSR-DARTS Parameters 4.0M #25 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-10 MSR-DARTS Search Time (GPU days) 0.3 #25 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-10 MSR-DARTS Top-1 Error Rate 2.54% #25 of 41 Archive leaderboard report
Neural Architecture Search ImageNet MSR-DARTS (CIFAR-10) Accuracy 76.1 #91 of 135 Archive leaderboard report
Neural Architecture Search ImageNet MSR-DARTS (CIFAR-10) MACs 632M #91 of 135 Archive leaderboard report
Neural Architecture Search ImageNet MSR-DARTS (CIFAR-10) Params 5.6M #91 of 135 Archive leaderboard report
Neural Architecture Search ImageNet MSR-DARTS (CIFAR-10) Top-1 Error Rate 23.9 #91 of 135 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

ConvolutionDARTS

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