Research map / Architectures and efficiency / Neural architecture search
Breaking the Curse of Space Explosion: Towards Efficient NAS with Curriculum 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 |
|---|---|---|---|
| Train the controller in a progressively growing search space rather than training from scratch in each fixed space (ablation) | CNAS · CIFAR-10 search stages | architecture test performance | Helped |
| Increase the number of candidate operations progressively rather than increasing the number of nodes (ablation) | CNAS · CIFAR-10 largest search space | test accuracy (%): 97.15% vs. 97.40% | Helped |
| Add operation warmup when introducing a new operation (ablation) | CNAS · CIFAR-10 search stages | architecture search performance | Helped |
| Vary the order in which candidate operations are introduced (ablation) | CNAS · CIFAR-10 | mean accuracy | No clear effect |
Closest papers by meaning
- Neural Architecture Generator Optimization (NeurIPS 2020 · similarity 0.89)
- Evaluating The Search Phase of Neural Architecture Search (ICLR 2020 · similarity 0.89)
- ReNAS: Relativistic Evaluation of Neural Architecture Search (CVPR 2021 · similarity 0.89)
- Insights from the Use of Previously Unseen Neural Architecture Search Datasets (CVPR 2024 · similarity 0.88)
- einspace: Searching for Neural Architectures from Fundamental Operations (NeurIPS 2024 · similarity 0.88)
- Towards Neural Architecture Search through Hierarchical Generative Modeling (ICML 2024 · 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.