Research map / Architectures and efficiency / Neural architecture search
Efficient Neural Architecture Search via Proximal Iterations
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 |
|---|---|---|---|
| search with 12 operations rather than 7 (ablation) | NASP · CIFAR-10 test | test error (%): 2.83±0.09 -> 2.44±0.04 | Helped |
| search with 12 operations rather than 7 (ablation) | NASP · ImageNet test | top1 test error (%): 27.2 -> 26.3 | Helped |
| search with more operations (ablation) | NASP · Tiny ImageNet test | top1 accuracy (%): 58.12 -> 58.32 | Helped |
| search with more operations (ablation) | NASP · Tiny ImageNet test | top5 accuracy (%): 77.62 -> 77.54 | Hurt |
| maintain discrete architectures and update weights only with selected operations | DARTS-style differentiable NAS · CIFAR-10 search | search time (GPU days): 4 -> 0.1 | Helped |
| remove the second-order approximation | NASP · CIFAR-10 search | time per epoch (seconds): 1315 -> - | Helped |
| use direct standard proximal updates instead of the NASP update (ablation) | NASP · CIFAR-10 | validation accuracy | Hurt |
| use lazy proximal updates instead of the NASP update (ablation) | NASP · CIFAR-10 | validation accuracy | Hurt |
| increase the model-complexity penalty (ablation) | NASP · CIFAR-10 | model size | Helped |
Closest papers by meaning
- Unifying and Boosting Gradient-Based Training-Free Neural Architecture Search (NeurIPS 2022 · similarity 0.91)
- Evaluating The Search Phase of Neural Architecture Search (ICLR 2020 · similarity 0.91)
- 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 0.90)
- HEP-NAS: Towards Efficient Few-shot Neural Architecture Search via Hierarchical Edge Partitioning (AAAI 2025 · similarity 0.90)
- Boosting Order-Preserving and Transferability for Neural Architecture Search: a Joint Architecture Refined Search and Fine-tuning Approach (CVPR 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.