Research map / Learning theory and algorithms / Sample complexity
On Performance Estimation in Automatic Algorithm Configuration
Shengcai Liu, Ke Tang, Yunwei Lei, Xin Yao
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 |
|---|---|---|---|
| Distribute runs as evenly as possible across training instances | Performance estimation in AAC · SATenstein-QCP, clasp-weighted-sequence, LKH-uniform-400, LKH-uniform-1000 | estimation error | Improved |
| Allocate runs greedily to instances, completing up to 5 runs on each before selecting another | Performance estimation in AAC · Four configuration scenarios | estimation error | Hurt |
| Select instances with replacement and run once per selected instance | Performance estimation in AAC · Four configuration scenarios | estimation error | Hurt |
| Increase the number of runs N | Performance estimation in AAC · Four configuration scenarios | uniform estimation error | Improved |
| Increase the number of training instances K | Performance estimation in AAC · Four configuration scenarios | uniform estimation error | Improved |
| Increase the number of considered configurations m | Uniform performance estimation · Four configuration scenarios | uniform estimation error | Hurt |
| Run configurations on half of the training instances | Performance estimation in AAC · Four configuration scenarios | estimation error | Improved |
Closest papers by meaning
- Refined bounds for algorithm configuration: The knife-edge of dual class approximability (ICML 2020 · similarity 0.85)
- ImpatientCapsAndRuns: Approximately Optimal Algorithm Configuration from an Infinite Pool (NeurIPS 2020 · similarity 0.83)
- Optimizer Benchmarking Needs to Account for Hyperparameter Tuning (ICML 2020 · similarity 0.82)
- AC-Band: A Combinatorial Bandit-Based Approach to Algorithm Configuration (AAAI 2023 · similarity 0.82)
- Towards Robustness and Explainability of Automatic Algorithm Selection (ICML 2025 · similarity 0.81)
- CapsAndRuns: An Improved Method for Approximately Optimal Algorithm Configuration (ICML 2019 · similarity 0.81)
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.
