Research map / Learning theory and algorithms / Prediction and decision losses
Enumerating Distinct Decision Trees
Salvatore Ruggieri
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 |
|---|---|---|---|
| replace SBE with PSBE (prune trees equal to the top tree) | SBE · benchmark datasets, m=2 | elapsed time: speedup of up to 100× | Improved |
| PSBE on high-dimensional p53Mutants | SBE · p53Mutants | elapsed time: 150.518 vs >1h | Improved |
| increase number of features | PSBE · Clean2 vs Sonar | time ratio PSBE/SBE: 0.020 vs 0.027 | Improved |
| order feature subsets by ascending frontier size | DTdistinct · low/medium dimensional datasets | ratio built/distinct trees: 1 to 1.35 | Improved |
| decrease stopping parameter m | DTdistinct · enumeration | elapsed time | Hurt |
| DTdistinct pruning on Anneal | DTdistinct · Anneal | enumeration time: less than 20 seconds for m = 16, less than 270 seconds for m = 8 | Improved |
| select features with SBE instead of all features | top tree · Adult | search error | Improved |
| select features with SBE instead of all features | top tree · Adult | cross-validation error (%): 15.74 -> 14.64 | Improved |
| use optimal feature subset instead of SBE | SBE · Adult | cross-validation error (%): 14.64 -> 14.31 | Improved |
| use optimal feature subset instead of SBE | SBE · Ionosphere | cross-validation error (%): 10.25 -> 10.72 | Hurt |
| use optimal feature subset instead of SBE | SBE · Anneal | cross-validation error (%): 1.14 -> 1.45 | Hurt |
| use optimal feature subset instead of SBE | SBE · Soybean | cross-validation error (%): 12.71 -> 10.62 | Improved |
Closest papers by meaning
- Complete Search for Feature Selection in Decision Trees (JMLR 2019 · similarity 0.92)
- The Influence of Dimensions on the Complexity of Computing Decision Trees (AAAI 2023 · similarity 0.88)
- Improving Decision Trees through the Lens of Parameterized Local Search (NeurIPS 2025 · similarity 0.86)
- Optimal Decision Tree Pruning Revisited: Algorithms and Complexity (ICML 2025 · similarity 0.86)
- Near-Optimal Decision Trees in a SPLIT Second (ICML 2025 · similarity 0.84)
- Learning Small Decision Trees with Few Outliers: A Parameterized Perspective (AAAI 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.
