Research map / Learning theory and algorithms / Sample complexity
Sample Complexity of Learning Heuristic Functions for Greedy-Best-First and A* Search
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 |
|---|---|---|---|
| Bound A* suboptimality using inconsistency along an optimal path | A* · Expected suboptimality over path-finding instances | complexity term: \tilde\mathrm{O}(H\sqrt{\frac{n^2 + \lg \frac{1}{\delta}}{N}}) -> \tilde\mathrm{O}(\hat H \sqrt{\frac{n + \lg \frac{1}{\ | Helped |
| Assume maximum out-degree at most d | A* · Fixed-vertex-set path-finding instances | pseudo-dimension upper bound: O(n^2\lg n) -> O(n^2\lg d) | Helped |
| Assume edge weights are non-negative integers bounded by ℓ | A* · Fixed-vertex-set path-finding instances | pseudo-dimension upper bound: O(n^2\lg n) -> O(n\lg(n\ell)) | Helped |
| Assume integer edge weights are bounded by poly(n) | A* · Fixed-vertex-set path-finding instances | pseudo-dimension upper bound: O(n^2\lg n) -> O(n \lg n) | Helped |
| Apply the analysis to heuristic functions restricted to maximum out-degree d | A* · Fixed-vertex-set path-finding instances | pseudo-dimension upper bound: O(n^2\lg n) -> O(n^2\lg d) | Helped |
Closest papers by meaning
- The Query Complexity of Local Search in Rounds on General Graphs (NeurIPS 2026 · similarity 0.87)
- Bayesian Optimization of Functions over Node Subsets in Graphs (NeurIPS 2024 · similarity 0.87)
- ROS: A GNN-based Relax-Optimize-and-Sample Framework for Max-$k$-Cut Problems (ICML 2025 · similarity 0.85)
- Improved Approximations for Hard Graph Problems using Predictions (ICML 2025 · similarity 0.85)
- Learning-Augmented Approximation Algorithms for Maximum Cut and Related Problems (NeurIPS 2024 · similarity 0.85)
- Sample Complexity of Algorithm Selection Using Neural Networks and Its Applications to Branch-and-Cut (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.