Research map / Architectures and efficiency / Neural architecture search
Understanding and Accelerating Neural Architecture Search With Training-Free and Theory-Grounded Metrics
Wuyang Chen, Xinyu Gong, Junru Wu, Yunchao Wei, Humphrey Shi, Zhicheng Yan, Yi Yang, Zhangyang Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add TEG training-free indicators as reward | FP-NAS · NAS-Bench-201 CIFAR-100 | test accuracy (%): 22.30 -> 70.36 | Improved |
| add TEG indicators | REINFORCE · NAS-Bench-201 CIFAR-100 | test accuracy (%): 68.40 -> 70.42 | Improved |
| add TEG indicators | Evolution · NAS-Bench-201 CIFAR-10 | test accuracy (%): 90.92 -> 91.00 | No clear effect |
| add TEG indicators | TE-NAS · NAS-Bench-201 CIFAR-100 | test accuracy (%): 71.24 -> 71.44 | No clear effect |
| add TEG indicators | REINFORCE · NAS-Bench-101 | test accuracy (%): 93.80 -> 94.11 | Improved |
| add TEG indicators | Evolution · NAS-Bench-101 | test accuracy (%): 92.17 -> 92.52 | Improved |
| add TEG indicators | FP-NAS · DARTS space ImageNet | top-1 error (%): 31.2 -> 23.7 | Improved |
| add TEG indicators | REINFORCE · DARTS space ImageNet | top-1 error (%): 28.2 -> 25.1 | Improved |
| add TEG indicators | Evolution · DARTS space ImageNet | top-1 error (%): 29.1 -> 26.3 | Improved |
| add TEG indicators | FP-NAS · DARTS space CIFAR-10 | test error (%): 4.61 -> 2.74 | Improved |
| add TEG indicators | Evolution · DARTS space CIFAR-10 | test error (%): 3.24 -> 3.16 | No clear effect |
| add trainability indicator kappa as reward vs 1-epoch training (ablation) | REINFORCE · NAS-Bench-201 CIFAR-100 | test accuracy (%): 68.4 -> 69.27 | Improved |
Closest papers by meaning
- Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective (ICLR 2021 · similarity 0.95)
- Unifying and Boosting Gradient-Based Training-Free Neural Architecture Search (NeurIPS 2022 · similarity 0.94)
- Insights from the Use of Previously Unseen Neural Architecture Search Datasets (CVPR 2024 · similarity 0.92)
- einspace: Searching for Neural Architectures from Fundamental Operations (NeurIPS 2024 · similarity 0.92)
- Efficient Few-Shot Neural Architecture Search by Counting the Number of Nonlinear Functions (AAAI 2025 · similarity 0.91)
- EG-NAS: Neural Architecture Search with Fast Evolutionary Exploration (AAAI 2024 · similarity 0.91)
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.
