Research map / Learning theory and algorithms / Fairness
Fair and Optimal Decision Trees: A Dynamic Programming Approach
Jacobus G.M. van der Linden, Mathijs Weerdt, Emir Demirović
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 |
|---|---|---|---|
| add pruning and dominance checks (ablation) | DPF · COMPAS recid., depth 4 | runtime: > 1h -> 9 | Improved |
| add pruning and dominance checks (ablation) | DPF · Dutch census, depth 3 | runtime: > 1h -> 5 | Improved |
| add pruning and dominance checks (ablation) | DPF · German credit, depth 4 | runtime: > 1h -> 741 | Improved |
| add pruning and dominance checks (ablation) | DPF · German credit, depth 3 | runtime: 8 -> 2 | No clear effect |
| add merge improvements (ablation) | DPF · Dutch census, depth 3 | runtime: 101 -> 5 | Improved |
| add merge improvements (ablation) | DPF · COMPAS recid., depth 4 | runtime: 394 -> 9 | Improved |
| add merge improvements (ablation) | DPF · German credit, depth 3 | runtime: 2 -> 2 | No clear effect |
| add nondom improvements (ablation) | DPF · Dutch census, depth 3 | runtime: 1814 -> 5 | Improved |
| add nondom improvements (ablation) | DPF · Bank Marketing, depth 3 | runtime: 319 -> 2 | Improved |
| use DPF instead of FairOCT MIP | FairOCT · 12 fairness datasets, depth 2 | runtime: COMPAS viol. recid.: 1594 -> < 1 | Improved |
| search the full Pareto front rather than a single tree | DPF · COMPAS recid., depth 4 | runtime: 9 -> 1659 | Hurt |
| increase minimum leaf node size (ablation) | DPF · depth 3 on Bank Marketing, Dutch census, OULAD | runtime | Improved |
Closest papers by meaning
- Generalized and Scalable Optimal Sparse Decision Trees (ICML 2020 · similarity 0.90)
- Necessary and Sufficient Conditions for Optimal Decision Trees using Dynamic Programming (NeurIPS 2023 · similarity 0.89)
- Near-Optimal Decision Trees in a SPLIT Second (ICML 2025 · similarity 0.88)
- Witty: An Efficient Solver for Computing Minimum-Size Decision Trees (AAAI 2025 · similarity 0.86)
- Piecewise Constant and Linear Regression Trees: An Optimal Dynamic Programming Approach (ICML 2024 · similarity 0.86)
- Enhancing Group Fairness in Online Settings Using Oblique Decision Forests (ICLR 2024 · similarity 0.86)
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.
