AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Connecting Interpretability and Robustness in Decision Trees through Separation

Michal Moshkovitz, Yao-Yuan Yang, Kamalika Chaudhuri

ICML 2021 · Learning theory and algorithms › Prediction and decision losses · approach: Optimal decision tree learning · 3 citations (OpenAlex)

Read the paper

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 changedWhereMeasuredEffect
Use BBM-RS rather than the competing interpretable methodsBBM-RS · 13 real-world datasetsinterpretation complexityImproved
Use BBM-RS rather than the competing interpretable methodsBBM-RS · 13 real-world datasetsempirical robustnessImproved
Use BBM-RS rather than the competing interpretable methodsBBM-RS · 13 real-world datasetstest accuracyMixed
Increase the noise level τ (ablation)BBM-RS on spambase · spambaseinterpretation complexity: 22.5 -> 2.3Improved
Increase the noise level τ (ablation)BBM-RS on spambase · spambaseempirical robustness: 0.006 -> 0.33Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy