AI Paper Atlas

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

Auditing Black-Box Prediction Models for Data Minimization Compliance

Bashir Rastegarpanah, Krishna P. Gummadi, Mark Crovella

NeurIPS 2021 · Learning theory and algorithms › Prediction and decision losses · approach: Provable post-hoc explanations · 4 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 TS, TTTS, Greedy or PM exploration instead of uniform explorationdata minimization auditor (Algorithm 1) · Digits/SVM, Census/DT, Nursery/DT at 1% levelnumber of system queriesImproved
use Greedy and PM instead of Thompson-sampling based TS and TTTSdata minimization auditor (Algorithm 1) · Digits/SVM, Census/DT, Nursery/DT at 1% levelnumber of system queriesImproved
use proposed exploration strategies instead of uniform exploration under a query budgetdata minimization measurement (Algorithm 2) · three prediction systems, 0.95 confidenceguaranteed data minimization levelImproved
use Greedy and PM instead of TS-based algorithms at small query budgetsdata minimization measurement (Algorithm 2) · three prediction systems, small budgetsguaranteed data minimization levelImproved
query-based audit instead of population auditdata minimization measurement (Algorithm 2) · three prediction systemsqueries needed to reach population-audit level: less than 5% of queries used by population auditImproved
use proposed exploration strategies instead of uniform on a system with an unused extra inputdata minimization auditor (Algorithm 1) · Census/DT with unused attributenumber of system queriesImproved
use Greedy instead of other exploration strategiesdata minimization auditor (Algorithm 1) · Census/DT with unused attributenumber of system queriesImproved

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