Research map / Architectures and efficiency / Neural architecture search
Unifying and Boosting Gradient-Based Training-Free Neural Architecture Search
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 |
|---|---|---|---|
| add BO-tuned unified objective (HNAS) on top of training-free metric | gradient-norm metric · NAS-Bench-201 ImageNet-16-120 | test accuracy (%): 44.44 -> 45.91 (NASWOT vs HNAS M_Grad) | Helped |
| use HNAS with GraSP metric instead of TE-NAS | training-free NAS · NAS-Bench-201 CIFAR-100 | test accuracy (%): 71.24 -> 72.59 | Helped |
| use HNAS instead of REA on CIFAR-100 | HNAS (M_Grad) · NAS-Bench-201 CIFAR-100 | test accuracy (%): 71.84 -> 71.75 | No clear effect |
| use HNAS instead of training-based NAS | training-based NAS (DrNAS) · NAS-Bench-201 | search cost (GPU sec.): 14887 -> 3006 | Helped |
| use HNAS instead of training-free NASWOT | training-free NAS · NAS-Bench-201 | search cost (GPU sec.): 306 -> 3006 | Hurt |
| use non-realizable generalization bound instead of realizable bound as objective (ablation) | training-free NAS objective · NAS-Bench-101 CIFAR-10 | correlation with test error | Helped |
| select wide instead of deep architectures | DARTS search space architectures · DARTS space | condition number / M_Trace | Helped |
Closest papers by meaning
- Per-Architecture Training-Free Metric Optimization for Neural Architecture Search (NeurIPS 2025 · similarity 0.94)
- Robustifying and Boosting Training-Free Neural Architecture Search (ICLR 2024 · similarity 0.93)
- Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective (ICLR 2021 · similarity 0.93)
- Efficient Few-Shot Neural Architecture Search by Counting the Number of Nonlinear Functions (AAAI 2025 · similarity 0.91)
- einspace: Searching for Neural Architectures from Fundamental Operations (NeurIPS 2024 · similarity 0.90)
- EG-NAS: Neural Architecture Search with Fast Evolutionary Exploration (AAAI 2024 · similarity 0.90)
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.