AI Paper Atlas

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

Bayesian Persuasion for Algorithmic Recourse

Keegan Harris, Valerie Chen, Joon Sik Kim, Ameet Talwalkar, Hoda Heidari, Steven Wu

NeurIPS 2022 · Learning theory and algorithms › Prediction and decision losses · approach: Adaptive testing and experiments · 1 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
recommend actions via the optimal signaling policy instead of revealing full information or no informationoptimal Bayesian persuasion policy · HELOC semi-syntheticdecision maker expected utilityImproved
increase prior variance sigma^2 of decision subjects' belief over the assessment rule (ablation)optimal signaling policy · HELOC semi-synthetic, sigma^2 = 0.1, 0.4, 1.0utility gap over baselinesImproved
raise action cost c(a) and lower feature change Delta x(a) (ablation)optimal signaling policy · HELOC grid c in {0,0.25,0.5}, Delta x in {0,0.5,1.0}decision maker total expected utilityHurt
lower action cost c(a) and raise feature change Delta x(a) (ablation)optimal signaling policy · HELOC griddecision maker total expected utilityImproved
optimal signaling vs baselines when action cost is high and feature change lowoptimal signaling policy · HELOC griddecision maker total expected utilityImproved

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