AI Paper Atlas

Research map / Multi-agent systems and games / Games and equilibria

Who Leads and Who Follows in Strategic Classification?

Tijana Zrnic, Eric Mazumdar, Shankar Sastry, Michael Jordan

NeurIPS 2021 · Multi-agent systems and games › Games and equilibria · approach: Strategic classification · 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
Let agents lead (decision-maker updates faster) instead of decision-maker leadingStrategic logistic regression with constrained agents · Simulated logistic regression, B=2, p in {0.1,0.5}average running risk (decision-maker and agents)Improved
Let agents lead instead of decision-maker leading when p=0.9 or B=1Strategic logistic regression with constrained agents · Simulated logistic regression, p=0.9 or B=1average running riskNo clear effect
Let agents lead in model with costly deviations, lambda=1Strategic logistic regression with quadratic deviation cost · Simulated logistic regression, 2-D, lambda=1average running riskImproved
Increase lambda to 20 and p to 0.9 in costly-deviation modelStrategic logistic regression with quadratic deviation cost · Simulated logistic regression, 2-Dgap between the two equilibriaHurt
Increase B and decrease pEquilibrium risk comparison, Bernoulli data with Gaussian features · Simulated, x0|y~N(4y-2,1)risk difference between equilibriaImproved

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