Convergence of Learning Dynamics in Information Retrieval Games

TL;DR

This paper models strategic authors in information retrieval as a game, analyzing how different ranking methods influence the convergence of authors' learning dynamics to stable equilibria.

Contribution

It introduces a game-theoretic framework for information retrieval, analyzing convergence properties under various ranking schemes, especially the probability ranking principle.

Findings

Under PRP, better-response dynamics converge to a pure Nash equilibrium.

Other ranking methods may prevent convergence of learning dynamics.

The study highlights the strategic implications of ranking algorithms.

Abstract

We consider a game-theoretic model of information retrieval with strategic authors. We examine two different utility schemes: authors who aim at maximizing exposure and authors who want to maximize active selection of their content (i.e. the number of clicks). We introduce the study of author learning dynamics in such contexts. We prove that under the probability ranking principle (PRP), which forms the basis of the current state of the art ranking methods, any better-response learning dynamics converges to a pure Nash equilibrium. We also show that other ranking methods induce a strategic environment under which such a convergence may not occur.