AI Paper Atlas

Research map / Learning theory and algorithms / Submodular and game algorithms

Decisions, Counterfactual Explanations and Strategic Behavior

Stratis Tsirtsis, Manuel Gomez Rodriguez

NeurIPS 2020 · Learning theory and algorithms › Submodular and game algorithms · approach: Submodular influence maximization · 14 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
Jointly optimize decision policy and counterfactual explanations (Algorithm 2) instead of only explanations for a fixed policystrategic decision maker · lending and credit datasetsutilityImproved
Choose explanations via greedy submodular maximization (Algorithm 1) instead of minimum-cost or diverse baselinesstrategic decision maker · lending and credit datasetsutilityImproved
Increase number of counterfactual explanations k (ablation)Algorithm 1 and 2 · lending datasetutilityImproved
Allow explanation leakage between individuals (higher leakage probability) (ablation)Algorithm 2 · lending datasetutilityNo clear effect
Replace cardinality constraint with partition matroid constraint over age groups (ablation)greedy explanation selection · credit datasetutilityMixed

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