Research map / Learning theory and algorithms / Prediction and decision losses
Optimal Sparse Decision Trees
Xiyang Hu, Cynthia Rudin, Margo Seltzer
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 |
|---|---|---|---|
| search over trees of any shape with a leaf penalty instead of complete binary trees of fixed depth (OSDT vs BinOCT) | optimal decision trees · Tic-Tac-Toe 8 leaves | accuracy: 76.722% -> 82.881% | Improved |
| search over trees of any shape with a leaf penalty instead of complete binary trees (OSDT vs BinOCT) | optimal decision trees · Monk1 | accuracy: 91.129% -> 100% | Improved |
| add lookahead and equivalent-points bounds (ablation) | OSDT · runtime and memory | time to optimum | Improved |
| schedule with curiosity instead of lower bound (ablation) | OSDT · COMPAS | time to find optimum | Improved |
| add extra irrelevant features (4 to 12) | OSDT · COMPAS scalability | fraction of runtime to reach optimum: about 75% -> about 5% | Improved |
| incremental computation, data structures and worklist ordering | OSDT · execution time | run time saved: >97% | Improved |
Closest papers by meaning
- Near-Optimal Decision Trees in a SPLIT Second (ICML 2025 · similarity 0.92)
- Branches: Efficiently Seeking Optimal Sparse Decision Trees via AO* (ICML 2025 · similarity 0.90)
- Optimal Decision Tree Pruning Revisited: Algorithms and Complexity (ICML 2025 · similarity 0.90)
- Learning Small Decision Trees with Few Outliers: A Parameterized Perspective (AAAI 2024 · similarity 0.88)
- Improving Decision Trees through the Lens of Parameterized Local Search (NeurIPS 2025 · similarity 0.88)
- Witty: An Efficient Solver for Computing Minimum-Size Decision Trees (AAAI 2025 · similarity 0.87)
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.
