Research map / Architectures and efficiency / Neural architecture search
TAPAS: Train-Less Accuracy Predictor for 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 |
|---|---|---|---|
| Remove dataset-difficulty characterization (DCN) when training and predicting on one dataset (ablation) | TAP · CIFAR-10, single-dataset prediction | prediction performance | No clear effect |
| Use dataset-difficulty characterization and filter experiments to datasets of similar difficulty (ablation) | TAPAS · Unseen-dataset prediction | prediction performance | Helped |
| Use TAPAS to search for architectures without training during the search | CNN architecture search on CIFAR-100 · CIFAR-100 | accuracy: +4% | Helped |
Closest papers by meaning
- Neural Architecture Search without Training (ICML 2021 · similarity 0.89)
- Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective (ICLR 2021 · similarity 0.89)
- Efficient Architecture Search by Network Transformation (AAAI 2018 · similarity 0.89)
- How Powerful are Performance Predictors in Neural Architecture Search? (NeurIPS 2021 · similarity 0.88)
- EcoNAS: Finding Proxies for Economical Neural Architecture Search (CVPR 2020 · similarity 0.88)
- Surprisingly Strong Performance Prediction with Neural Graph Features (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.