Research map / Learning theory and algorithms / Prediction and decision losses
Algorithmic Assurance: An Active Approach to Algorithmic Testing using Bayesian Optimisation
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 Bayesian optimisation to search for maximal deviation instead of the worst training-set error | alloy phase neural network · Alloy phase NN, single-task | max RMSE: 0.27 -> 0.59 | Helped |
| use EXP3BO bandit-guided search instead of the worst training-set error | alloy phase neural network · Alloy phase NN, multi-task | max RMSE: 0.75 -> 1.05 | Helped |
| use BO over distortion parameters instead of grid search | LeNet-5 on distorted MNIST · Distorted MNIST, single-task | max error %: 5.7% -> 7.1% | Helped |
| EXP3BO instead of round-robin, random categorical BO and SMAC | multi-task algorithmic testing, alloy phases · Alloy phase NN, multi-task | RMSE vs iterations | Helped |
| EXP3BO instead of round-robin and random categorical BO | multi-task algorithmic testing, digits · Distorted MNIST, multi-task | error % vs iterations | No clear effect |
Closest papers by meaning
- Practical Bayesian Algorithm Execution via Posterior Sampling (NeurIPS 2024 · similarity 0.85)
- Conformal Validity Guarantees Exist for Any Data Distribution (and How to Find Them) (ICML 2024 · similarity 0.85)
- Towards Robustness and Explainability of Automatic Algorithm Selection (ICML 2025 · similarity 0.84)
- Learning to Discover at Test Time (ICML 2026 · similarity 0.84)
- A Survey of Learning Criteria Going beyond the Usual Risk (Abstract Reprint) (AAAI 2024 · similarity 0.83)
- What If We Allocate Test-Time Compute Adaptively? (ICML 2026 · similarity 0.83)
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.