Performative Prediction on Games and Mechanism Design

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Góis, António, Mofakhami, Mehrnaz, Santos, Fernando P., Gidel, Gauthier, Lacoste-Julien, Simon
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916616025931776
author Góis, António
Mofakhami, Mehrnaz
Santos, Fernando P.
Gidel, Gauthier
Lacoste-Julien, Simon
author_facet Góis, António
Mofakhami, Mehrnaz
Santos, Fernando P.
Gidel, Gauthier
Lacoste-Julien, Simon
contents Agents often have individual goals which depend on a group's actions. If agents trust a forecast of collective action and adapt strategically, such prediction can influence outcomes non-trivially, resulting in a form of performative prediction. This effect is ubiquitous in scenarios ranging from pandemic predictions to election polls, but existing work has ignored interdependencies among predicted agents. As a first step in this direction, we study a collective risk dilemma where agents dynamically decide whether to trust predictions based on past accuracy. As predictions shape collective outcomes, social welfare arises naturally as a metric of concern. We explore the resulting interplay between accuracy and welfare, and demonstrate that searching for stable accurate predictions can minimize social welfare with high probability in our setting. By assuming knowledge of a Bayesian agent behavior model, we then show how to achieve better trade-offs and use them for mechanism design.
format Preprint
id arxiv_https___arxiv_org_abs_2408_05146
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Performative Prediction on Games and Mechanism Design
Góis, António
Mofakhami, Mehrnaz
Santos, Fernando P.
Gidel, Gauthier
Lacoste-Julien, Simon
Machine Learning
Computer Science and Game Theory
Multiagent Systems
Agents often have individual goals which depend on a group's actions. If agents trust a forecast of collective action and adapt strategically, such prediction can influence outcomes non-trivially, resulting in a form of performative prediction. This effect is ubiquitous in scenarios ranging from pandemic predictions to election polls, but existing work has ignored interdependencies among predicted agents. As a first step in this direction, we study a collective risk dilemma where agents dynamically decide whether to trust predictions based on past accuracy. As predictions shape collective outcomes, social welfare arises naturally as a metric of concern. We explore the resulting interplay between accuracy and welfare, and demonstrate that searching for stable accurate predictions can minimize social welfare with high probability in our setting. By assuming knowledge of a Bayesian agent behavior model, we then show how to achieve better trade-offs and use them for mechanism design.
title Performative Prediction on Games and Mechanism Design
topic Machine Learning
Computer Science and Game Theory
Multiagent Systems
url https://arxiv.org/abs/2408.05146