Research map / Architectures and efficiency / Neural architecture search
Multinomial Distribution Learning for Effective Neural Architecture Search
Xiawu Zheng, Rongrong Ji, Lang Tang, Baochang Zhang, Jianzhuang Liu, Qi Tian
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 |
|---|---|---|---|
| use MdeNAS multinomial distribution search instead of random sampling in the same space | random sampling · CIFAR-10 | test error (%): 3.49 -> 2.55 | Improved |
| use MdeNAS instead of NASNet-A search | NASNet-A · CIFAR-10 | search cost (GPU days): 1800 -> 0.16 | Improved |
| use MdeNAS instead of DARTS second order | DARTS · CIFAR-10 | test error (%): 2.83 -> 2.55 | Improved |
| use MdeNAS instead of Path-level NAS | Path-level NAS · CIFAR-10 | test error (%): 2.49 -> 2.55 | Hurt |
| search directly on ImageNet with MdeNAS instead of Proxyless (GPU) | Proxyless (GPU) · ImageNet mobile (searched directly on ImageNet) | top-1 accuracy (%): 74.8 -> 75.2 | Improved |
| search directly on ImageNet with MdeNAS instead of Proxyless (CPU) | Proxyless (CPU) · ImageNet mobile (searched directly on ImageNet) | top-1 accuracy (%): 74.1 -> 74.1 | No clear effect |
| search directly on ImageNet with MdeNAS (GPU) instead of Proxyless (GPU) latency | Proxyless (GPU) · ImageNet mobile (searched directly on ImageNet) | GPU latency (ms): 5.1ms -> 4.9ms | Improved |
| transfer CIFAR-10 cell instead of AmoebaNet-C | AmoebaNet-C · ImageNet mobile (searched on CIFAR-10, transferred) | top-1 accuracy (%): 75.7 -> 74.5 | Hurt |
| evaluate architectures early in training (ranking hypothesis) | architecture ranking · CIFAR-10 | Kendall tau: 0.474 | Improved |
Closest papers by meaning
- Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective (ICLR 2021 · similarity 0.90)
- Distribution Consistent Neural Architecture Search (CVPR 2022 · similarity 0.89)
- DDPNAS: Efficient Neural Architecture Search via Dynamic Distribution Pruning (IJCV 2023 · similarity 0.89)
- MIGO-NAS: Towards Fast and Generalizable Neural Architecture Search (TPAMI 2021 · similarity 0.89)
- Learning Versatile Neural Architectures by Propagating Network Codes (ICLR 2022 · similarity 0.89)
- Efficient Few-Shot Neural Architecture Search by Counting the Number of Nonlinear Functions (AAAI 2025 · similarity 0.88)
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.
