Research map / Architectures and efficiency / Neural architecture search
BayesNAS: A Bayesian Approach for 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 |
|---|---|---|---|
| reduce λwᵒ from 0.01 to 0.005 (ablation) | BayesNAS · CIFAR-10 | test error (%): 3.02±0.04 -> 2.81±0.04 | Helped |
| reduce λwᵒ from 0.01 to 0.007 (ablation) | BayesNAS · ImageNet mobile setting | top-1 test error (%): 28.1 -> 27.3 | Helped |
| reduce λwᵒ from 0.007 to 0.005 (ablation) | BayesNAS · ImageNet mobile setting | top-5 test error (%): 8.4 -> 8.9 | Hurt |
| use Bayesian architecture search with uncertainty-based pruning | CIFAR-10 · CIFAR-10 | search cost (GPU days): 0.2 | Helped |
Closest papers by meaning
- Posterior-Guided Neural Architecture Search (AAAI 2020 · similarity 0.92)
- Meta Architecture Search (NeurIPS 2019 · similarity 0.92)
- ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding (NeurIPS 2020 · similarity 0.91)
- Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS (NeurIPS 2020 · similarity 0.91)
- Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective (ICLR 2021 · similarity 0.91)
- Efficient Few-Shot Neural Architecture Search by Counting the Number of Nonlinear Functions (AAAI 2025 · similarity 0.89)
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.