Research map / Learning theory and algorithms / Optimal transport
Neural Architecture Search with Bayesian Optimisation and Optimal Transport
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 |
|---|---|---|---|
| Use NNBO instead of random search | Neural architecture search · Blog feedback | MSE: 0.780 -> 0.731 | Helped |
| Use NNBO instead of random search | Neural architecture search · Indoor location | MSE: 0.115 -> 0.117 | Hurt |
| Use NNBO instead of the evolutionary algorithm | Neural architecture search · Slice localisation | MSE: 0.733 -> 0.615 | Helped |
| Use NNBO instead of the evolutionary algorithm | Neural architecture search · Naval propulsion | MSE: 0.0079 -> 0.0075 | Helped |
| Use NNBO instead of random search | Neural architecture search · Protein tertiary structure | MSE: 0.948 -> 0.902 | Helped |
| Use NNBO instead of the evolutionary algorithm | Neural architecture search · News popularity | MSE: 0.758 -> 0.752 | Helped |
| Use NNBO instead of random search | CNN architecture search · CIFAR-10 | classification error: 0.1342 -> 0.1209 | Helped |
| Use NNBO instead of the evolutionary algorithm | CNN architecture search · CIFAR-10, 150K iterations | classification error: 0.0915 -> 0.0869 | Helped |
Closest papers by meaning
- BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search (AAAI 2021 · similarity 0.91)
- Robustifying and Boosting Training-Free Neural Architecture Search (ICLR 2024 · similarity 0.86)
- Efficient Hyperparameter Optimization with Adaptive Fidelity Identification (CVPR 2024 · similarity 0.85)
- BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RL (ICLR 2025 · similarity 0.85)
- Posterior Inference with Diffusion Models for High-dimensional Black-box Optimization (ICML 2025 · similarity 0.85)
- A Study of Bayesian Neural Network Surrogates for Bayesian Optimization (ICLR 2024 · similarity 0.85)
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.