Convergence of Learning Dynamics in Information Retrieval Games

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.

[1]  Chang Liu,et al.  The impacts of time constraint on users' search strategy during search process , 2016, ASIST.

[2]  Moshe Tennenholtz,et al.  Information Retrieval Meets Game Theory: The Ranking Competition Between Documents' Authors , 2017, SIGIR.

[3]  Craig Boutilier,et al.  The Dynamics of Reinforcement Learning in Cooperative Multiagent Systems , 1998, AAAI/IAAI.

[4]  I. Milchtaich,et al.  Congestion Games with Player-Specific Payoff Functions , 1996 .

[5]  Oren Kurland,et al.  Query-Performance Prediction Using Minimal Relevance Feedback , 2013, ICTIR.

[6]  Moshe Tennenholtz,et al.  Strong mediated equilibrium , 2006, Artif. Intell..

[7]  Thorsten Joachims,et al.  Accurately interpreting clickthrough data as implicit feedback , 2005, SIGIR '05.

[8]  Hector Garcia-Molina,et al.  Web Spam Taxonomy , 2005, AIRWeb.

[9]  Y. Freund,et al.  Adaptive game playing using multiplicative weights , 1999 .

[10]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[11]  R. A. Bradley,et al.  RANK ANALYSIS OF INCOMPLETE BLOCK DESIGNS , 1952 .

[12]  Ron Lavi,et al.  Algorithmic Mechanism Design , 2008, Encyclopedia of Algorithms.

[13]  Moshe Tennenholtz,et al.  Competing Prediction Algorithms , 2018, ArXiv.

[14]  R. A. Bradley,et al.  RANK ANALYSIS OF INCOMPLETE BLOCK DESIGNS THE METHOD OF PAIRED COMPARISONS , 1952 .

[15]  Haipeng Luo,et al.  Fast Convergence of Regularized Learning in Games , 2015, NIPS.

[16]  L. Shapley,et al.  Potential Games , 1994 .

[17]  S. Robertson.  The probability ranking principle in IR , 1997 .

[18]  Moshe Tennenholtz,et al.  A Game-Theoretic Approach to Recommendation Systems with Strategic Content Providers , 2018, NeurIPS.

[19]  H. Hotelling.  Stability in Competition , 1929 .

[21]  Georgios Piliouras,et al.  Multiplicative Weights Update with Constant Step-Size in Congestion Games: Convergence, Limit Cycles and Chaos , 2017, NIPS.

[22]  Nicholas R. Jennings,et al.  Convergence to Equilibria in Plurality Voting , 2010, AAAI.

[23]  Moshe Tennenholtz,et al.  The Probability Ranking Principle is Not Optimal in Adversarial Retrieval Settings , 2015, ICTIR.

[24]  Tommi S. Jaakkola,et al.  Learning Tree Structured Potential Games , 2016, NIPS.

[25]  Omer Lev,et al.  Convergence of iterative voting , 2012, AAMAS.

[26]  Itai Ashlagi,et al.  Mediators in position auctions , 2007, EC '07.

[27]  Ran Ben Basat.  A Game Theoretic Analysis of the Adversarial Retrieval Setting , 2017 .

[28]  Gábor Lugosi,et al.  Prediction, learning, and games , 2006 .

[29]  R. Rosenthal.  A class of games possessing pure-strategy Nash equilibria , 1973 .

[30]  Avi Goldfarb,et al.  How Is the Mobile Internet Different? Search Costs and Local Activities , 2013, Inf. Syst. Res..

[31]  Claire Mathieu,et al.  Convergence of Position Auctions under Myopic Best-Response Dynamics , 2014, TEAC.

[32]  R. Aumann.  Subjectivity and Correlation in Randomized Strategies , 1974 .

[33]  Moshe Tennenholtz,et al.  From Recommendation Systems to Facility Location Games , 2018, AAAI.

[34]  Tsuyoshi Murata,et al.  {m , 1934, ACML.