Papers › $μ$DARTS: Model Uncertainty-Aware Differentiable Architecture Search

$μ$DARTS: Model Uncertainty-Aware Differentiable Architecture Search

24 Jul 2021arXiv:2107.11500archive 2025-07-28

Biswadeep Chakraborty, Saibal Mukhopadhyay

We present a Model Uncertainty-aware Differentiable ARchiTecture Search (μDARTS) that optimizes neural networks to simultaneously achieve high accuracy and low uncertainty. We introduce concrete dropout within DARTS cells and include a Monte-Carlo regularizer within the training loss to optimize the concrete dropout probabilities. A predictive variance term is introduced in the validation loss to enable searching for architecture with minimal model uncertainty. The experiments on CIFAR10, CIFAR100, SVHN, and ImageNet verify the effectiveness of μDARTS in improving accuracy and reducing uncertainty compared to existing DARTS methods. Moreover, the final architecture obtained from μDARTS shows higher robustness to noise at the input image and model parameters compared to the architecture obtained from existing DARTS methods.

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 Searchmodel

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Neural Architecture Search CIFAR-10 μDARTS FLOPS 602M #37 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-10 μDARTS Search Time (GPU days) 0.1 #37 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-10 μDARTS Top-1 Error Rate 3.277% #37 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-100 μDARTS PARAMS 602M #12 of 13 Archive leaderboard report
Neural Architecture Search CIFAR-100 μDARTS Percentage Error 19.39 #12 of 13 Archive leaderboard report
Neural Architecture Search CIFAR-100 μDARTS Search Time (GPU days) 1.57 #12 of 13 Archive leaderboard report
Neural Architecture Search ImageNet μDARTS Accuracy 78.76 #43 of 135 Archive leaderboard report
Neural Architecture Search ImageNet μDARTS Params 602M #43 of 135 Archive leaderboard report
Neural Architecture Search ImageNet μDARTS Top-1 Error Rate 21.24 #43 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

Concrete DropoutDARTSDropout

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