AI Paper Atlas

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

Knowledge Refinement via Rule Selection

Phokion G. Kolaitis, Lucian Popa, Kun Qian

AAAI 2019 · Learning theory and algorithms › Prediction and decision losses · approach: Data attribution and recourse · 2 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
Represent FP minimization as Red-Blue Set CoverRule selection FP · Rule selection FPapproximation properties: 2\sqrt{|\mathcal{C}|\log{|J|}}; 2^{\log^{1-\epsilon}({|\mathcal{C}|})}Mixed
Represent FP+FN minimization as Positive-Negative Partial Set CoverRule selection FP+FN · Rule selection FP+FNapproximation properties: 2\sqrt{(|\mathcal{C}|+|J|)\log{|J|}}; 2^{\log^{1-\epsilon}({|J|})}Mixed
Account for both false positives and false negativesRule selection · Rule selection FP+FNdecision complexity: NP-completeMixed
Evaluate error and rule-set size as separate Pareto objectivesRule selection · Pareto front membership FP+FNdecision complexity: DP-completeMixed
Minimize rule-set size after minimizing errorRule selection · Bi-level optimal value FP+FNdecision complexity: DP-completeMixed

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