AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

Necessary and Sufficient Conditions for Optimal Decision Trees using Dynamic Programming

NeurIPS 2023 · Learning theory and algorithms › Combinatorial and search optimization · approach: Predict-then-optimize learning · 2 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
STreeD instead of TMDP for cost-sensitive classificationcost-sensitive decision trees · 15 datasets, 3 setups (45 scenarios)out-of-sample cost: 21 out of 45Helped
STreeD instead of MurTree (nonlinear) for F1-scoreoptimal decision trees · 25 binary classification datasets, depth 3-4runtimeHelped
STreeD instead of DL8.5 for accuracyoptimal decision trees · 25 datasets, depth 4-5runtimeHelped
STreeD instead of MurTree for accuracyoptimal decision trees · 25 datasets, depth 4-5runtime: 1.25 fasterHurt
STreeD instead of MIP methods (Jo-PPG-MIP, CAIPWL-opt) for prescriptive policy generationprescriptive trees · Warfarin and syntheticruntimeHelped
STreeD instead of DPF for demographic parityfair decision trees · 12 datasets, depth 1-3runtimeHurt
STreeD instead of MIP methods for demographic parityfair decision trees · 12 datasets, depth 1-3runtimeHelped

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