Research map / Bandits and online learning / Online convex optimization and games
On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach
Dennis Wei, Rahul Nair, Amit Dhurandhar, Kush R. Varshney, Elizabeth M. Daly, Moninder Singh
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 |
|---|---|---|---|
| Increase certification radius r from 0.0 to 0.1 (ablation) | Deviation maximization · HMDA, EBM vs DT | maximizing aus_1 / loan_to_value: 3 -> 1 | Mixed |
| Increase certification radius r to 0.4 (ablation) | Deviation maximization · HMDA, EBM vs DT | maximizing debt-to-income (%): 46.0 -> [52. 52.] | Mixed |
| Increase certification radius r on Adult Income (ablation) | Deviation maximization · Adult Income, EBM vs DT | maximizing capital loss: [1598, 1759] | Improved |
| Increase number of trees in Random Forest (ablation) | Random Forest · Maximum deviation upper bound | maximum deviation | Improved |
| Use logistic regression instead of EBM as alternative model | LR vs decision tree · HMDA | balanced accuracy | Hurt |
Closest papers by meaning
- What makes an Ensemble (Un) Interpretable? (ICML 2025 · similarity 0.84)
- Enhancing Performance of Explainable AI Models with Constrained Concept Refinement (ICML 2025 · similarity 0.84)
- SMLE: Safe Machine Learning via Embedded Overapproximation (AAAI 2025 · similarity 0.84)
- Local vs. Global Interpretability: A Computational Complexity Perspective (ICML 2024 · similarity 0.84)
- A Survey of Learning Criteria Going beyond the Usual Risk (Abstract Reprint) (AAAI 2024 · similarity 0.84)
- Multistage Defer Trees for Hybrid Interpretability: If at First You Can't Succeed, Tree Again (NeurIPS 2026 · 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.
