Research map / Optimization / Optimizers
How the Duration of the Learning Period Affects the Performance of Random Gradient Selection Hyper-Heuristics
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 |
|---|---|---|---|
| increase GRG learning period from 1 to 2500 (short but growing with n) (ablation) | GRG · OneMax n=10^6 | avg runtime / (n ln n): 1.820 -> 1.589 | Helped |
| set GRG learning period tau >= n instead of sublinear (ablation) | GRG with RLS1,RLS3 · OneMax | expected runtime | Hurt |
| set GRG learning period tau >= (1+eps) n ln n instead of o(n) (ablation) | GRG with RLS1,RLSk · RIDGE | expected runtime: (1 +- o(1)) 2n^2 -> (1+o(1)) n^2 | Helped |
| use adaptive learning period (ARG) instead of static tau | GRG · OneMax | avg runtime / (n ln n): remains below 1.86 | Helped |
| use F=1.5 instead of F=1+1/sqrt(ln n) in ARG (ablation) | ARG · OneMax | runtime | Helped |
Closest papers by meaning
- On the Time Complexity of Algorithm Selection Hyper-Heuristics for Multimodal Optimisation (AAAI 2019 · similarity 0.90)
- Gradient Span Algorithms Make Predictable Progress in High Dimension (NeurIPS 2026 · similarity 0.84)
- Understanding High-Dimensional Bayesian Optimization (ICML 2025 · similarity 0.84)
- Bayesian Optimisation with Unknown Hyperparameters: Regret Bounds Logarithmically Closer to Optimal (NeurIPS 2024 · similarity 0.84)
- HSEvo: Elevating Automatic Heuristic Design with Diversity-Driven Harmony Search and Genetic Algorithm Using LLMs (AAAI 2025 · similarity 0.84)
- The High Line: Exact Risk and Learning Rate Curves of Stochastic Adaptive Learning Rate Algorithms (NeurIPS 2024 · similarity 0.84)
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.