Research map / Learning theory and algorithms / Submodular and game algorithms
Learning Interpretable Decision Rule Sets: A Submodular Optimization Approach
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 |
|---|---|---|---|
| Use submodular rule-set learning instead of the strongest reported baseline | Binary classification across the evaluated datasets · 20 public datasets | accuracy | Mixed |
| Use the proposed method rather than Random forest | Submodular rule sets · tic-tac-toe and mushroom | accuracy (%): 100.0 vs 100.0 on tic-tac-toe; 100.0 vs 100.0 on mushroom | No clear effect |
| Use the proposed method rather than the best baseline | Submodular rule sets · liver | accuracy (%): 69.5 vs 73.9 | Hurt |
| Use the proposed method rather than the best baseline | Submodular rule sets · heart | accuracy (%): 82.2 vs 82.8 | Hurt |
| Use the proposed method rather than RIPPER | Submodular rule sets · COMPAS | number of rules: 12.0 -> 5.5 | Helped |
| Penalize overlap among rules in the objective | Submodular rule sets · Evaluated datasets | overlap among rules | Helped |
| Solve rule-construction subproblems approximately instead of with BnB | Submodular rule-set learner · tic-tac-toe, transfusion, heart, ILPD, mushroom | objective V(S): 433.78 vs 433.78; 12.00 vs 12.00; 99.48 vs 99.48; 217.00 vs 217.00; 3908.00 vs 3908.00 | No clear effect |
| Solve rule-construction subproblems approximately instead of with BnB | Submodular rule-set learner · COMPAS | objective V(S): 563.00 vs 642.57 | Hurt |
| Solve rule-construction subproblems approximately instead of with BnB | Submodular rule-set learner · FICO-binary | objective V(S): 1977.00 vs 1919.00 | Helped |
Closest papers by meaning
- Learning Accurate and Interpretable Decision Rule Sets from Neural Networks (AAAI 2021 · similarity 0.86)
- Interpretable Preference Learning: A Game Theoretic Framework for Large Margin On-Line Feature and Rule Learning (AAAI 2019 · similarity 0.85)
- Near-Optimal Decision Trees in a SPLIT Second (ICML 2025 · similarity 0.83)
- Online Two-Stage Submodular Maximization (NeurIPS 2025 · similarity 0.83)
- Optimal Decision Tree Pruning Revisited: Algorithms and Complexity (ICML 2025 · similarity 0.83)
- Corporate Needs You to Find the Difference: Revisiting Submodular and Supermodular Ratio Optimization Problems (NeurIPS 2025 · similarity 0.83)
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.