Research map / Learning theory and algorithms / Prediction and decision losses
Falling Trees: A Model Class for Interpretable Risk Prioritization
Varun Babbar, Zachery Boner, Margo Seltzer, Cynthia Rudin
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 |
|---|---|---|---|
| raise branching penalty mu from 0 toward 0.1 (ablation) | GRAVITree · four datasets | normalized Colless index | Improved |
| raise branching penalty mu (ablation) | GRAVITree · four datasets | Rashomon set size and runtime | Improved |
| allow branching (mu=0.01) instead of falling rule lists (mu=1) (ablation) | GRAVITree · Adult | test loss: 0.290 -> 0.204 | Improved |
| allow branching (mu=0.01) instead of falling rule lists (mu=1) (ablation) | GRAVITree · MGH | test loss: 0.232 -> 0.061 | Improved |
| allow branching (mu=0.01) instead of falling rule lists (mu=1) (ablation) | GRAVITree · Car Evaluation | decision sparsity on positives: 1.07 -> 2.09 | Hurt |
| allow branching (mu=0.01) instead of falling rule lists (mu=1) (ablation) | GRAVITree · 21 datasets | false negative rate | Mixed |
| use falling trees instead of unconstrained sparse trees | GRAVITree vs TreeFARMS · MGH | test loss: 0.031 -> 0.061 | Hurt |
| use falling trees instead of unconstrained sparse trees | GRAVITree vs TreeFARMS · Mushroom | decision sparsity on positives: 3.63 -> 2.51 | Improved |
| use falling trees instead of unconstrained sparse trees | GRAVITree vs TreeFARMS · Adult | decision sparsity on positives: 2.94 -> 3.39 | Hurt |
Closest papers by meaning
- Multistage Defer Trees for Hybrid Interpretability: If at First You Can't Succeed, Tree Again (NeurIPS 2026 · similarity 0.86)
- Near-Optimal Decision Trees in a SPLIT Second (ICML 2025 · similarity 0.84)
- SORTeD Rashomon Sets of Sparse Decision Trees: Anytime Enumeration (NeurIPS 2025 · similarity 0.84)
- Risk Horizons: Structured Hypothesis Spaces for Longitudinal Clinical Prediction (NeurIPS 2026 · similarity 0.83)
- Leveraging Predictive Equivalence in Decision Trees (ICML 2025 · similarity 0.83)
- Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agents (ICML 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.
