Research map / Learning theory and algorithms / Sample complexity
From Understanding Genetic Drift to a Smart-Restart Mechanism for Estimation-of-Distribution Algorithms
Weijie Zheng, Benjamin Doerr
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 smart-restart cGA instead of parallel-run cGA on OneMax and LeadingOnes | cGA with automatic population size · OneMax (n=100), LeadingOnes (n=50), all noise levels | runtime (fitness evaluations) | Improved |
| use population size below the genetic-drift threshold (ablation) | original cGA · OneMax (n=100) | runtime: drastic losses when mu is a factor of four or more below optimum | Hurt |
| increase population size beyond the optimum (ablation) | original cGA · four benchmarks | runtime: roughly linear increase | Hurt |
| increase noise variance (ablation) | original cGA · OneMax (n=100) | optimal population size: optimal population size increases with the noise level | Hurt |
| use budget factor 1/ln n instead of 16 in smart-restart (ablation) | smart-restart cGA · LeadingOnes (n=50) | runtime | Mixed |
| use update factor U=2 instead of sqrt(2) (ablation) | smart-restart cGA · earlier experiments | runtime | Improved |
Closest papers by meaning
- From Understanding Genetic Drift to a Smart-Restart Mechanism for Estimation-of-Distribution Algorithms (Journal Track) (AAAI 2025 · similarity 0.99)
- Runtime Analysis of the (μ + 1) GA: Provable Speed-Ups from Strong Drift towards Diverse Populations (AAAI 2024 · similarity 0.85)
- Statistical Properties of Robust Satisficing (ICML 2024 · similarity 0.82)
- Towards Running Time Analysis of Interactive Multi-Objective Evolutionary Algorithms (AAAI 2024 · similarity 0.82)
- Speeding Up the NSGA-II with a Simple Tie-Breaking Rule (AAAI 2025 · similarity 0.82)
- Optimistic Algorithms for Adaptive Estimation of the Average Treatment Effect (ICML 2025 · similarity 0.82)
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.
