Research map / Architectures and efficiency / Neural architecture search
Differentiable Architecture Search With Random Features
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Train only BN affine weights in the supernet while freezing convolution weights (ablation) | DARTS · NAS-Bench-201 CIFAR-10 | test accuracy: 54.30% to 94.36% | Helped |
| Train only BN affine weights in the supernet while freezing convolution weights (ablation) | DARTS · NAS-Bench-201 CIFAR-100 | test accuracy: 15.61% to 72.94% | Helped |
| Train only BN affine weights in the supernet while freezing convolution weights (ablation) | DARTS · DARTS search space ImageNet | top-1 test error: 26.9/8.7 to 24.0/7.2 | Helped |
| Use random-feature training with PC-DARTS and search directly on ImageNet | PC-DARTS · ImageNet-1K mobile setting | top-5 test error: 7.3 to 7.1 | Helped |
| Use random-feature training with PC-DARTS and search directly on ImageNet | PC-DARTS · ImageNet-1K mobile setting | top-1 test error: 23.9 to 23.9 | No clear effect |
| Train only BN affine weights rather than convolution and BN weights (ablation) | DARTS supernet · CIFAR-10, CIFAR-100, SVHN across RobustDARTS S1-S4 | test error | Mixed |
| Train convolution weights and BN affine weights instead of only BN affine weights (ablation) | DARTS supernet · NAS-Bench-201 CIFAR-10 | test accuracy: 94.36 vs 92.28 | Hurt |
Closest papers by meaning
- iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients (ICML 2021 · similarity 0.92)
- BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule (CVPR 2022 · similarity 0.92)
- PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search (ICLR 2020 · similarity 0.92)
- IS-DARTS: Stabilizing DARTS through Precise Measurement on Candidate Importance (AAAI 2024 · similarity 0.88)
- Efficient Few-Shot Neural Architecture Search by Counting the Number of Nonlinear Functions (AAAI 2025 · similarity 0.88)
- Subnet-Aware Dynamic Supernet Training for Neural Architecture Search (CVPR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.