AI Paper Atlas

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

Scalable Bayesian Rule Lists

Hongyu Yang, Cynthia Rudin, Margo Seltzer

ICML 2017 · Learning theory and algorithms › Prediction and decision losses · approach: Optimal decision tree learning · 9 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use bit-vector logical operations instead of set operations (ablation)SBRL rule-list evaluation · UCI adult, 10-fold runtime experimentruntime: approximately 50%Improved
Replace the original Python implementation with the optimized C/GMP implementation (ablation)SBRL · UCI adult, 10-fold runtime experimentruntime: over two orders of magnitude fasterImproved
Apply the theoretical prefix bound to reject prefixes that cannot beat the current best posteriorSBRL search · Rule-list optimizationruntime: full order of magnitude speedupImproved
Use SBRL instead of CARTClassifier runtime · USCensus1990, 1 million data points and 1 thousand rulesruntime: 2700 vs 2000Hurt
Use SBRL instead of CARTClassifier runtime · USCensus1990, 50 thousand data points and 50 thousand rulesruntime: 9000 vs 84Hurt
Use SBRL rather than CART or C4.5Sparse classifier · AdultAUCImproved
Use SBRL rather than untuned CART, CBA, or CMARClassifier · MushroomAUCImproved

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