On the Convergence of Learning Algorithms in Bayesian Auction Games

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bichler, Martin, Lunowa, Stephan B., Oberlechner, Matthias, Pieroth, Fabian R., Wohlmuth, Barbara
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929634330804224
author Bichler, Martin
Lunowa, Stephan B.
Oberlechner, Matthias
Pieroth, Fabian R.
Wohlmuth, Barbara
author_facet Bichler, Martin
Lunowa, Stephan B.
Oberlechner, Matthias
Pieroth, Fabian R.
Wohlmuth, Barbara
contents Equilibrium problems in Bayesian auction games can be described as systems of differential equations. Depending on the model assumptions, these equations might be such that we do not have a rigorous mathematical solution theory. The lack of analytical or numerical techniques with guaranteed convergence for the equilibrium problem has plagued the field and limited equilibrium analysis to rather simple auction models such as single-object auctions. Recent advances in equilibrium learning led to algorithms that find equilibrium under a wide variety of model assumptions. We analyze first- and second-price auctions where simple learning algorithms converge to an equilibrium. The equilibrium problem in auctions is equivalent to solving an infinite-dimensional variational inequality (VI). Monotonicity and the Minty condition are the central sufficient conditions for learning algorithms to converge to an equilibrium in such VIs. We show that neither monotonicity nor pseudo- or quasi-monotonicity holds for the respective VIs. The second-price auction's equilibrium is a Minty-type solution, but the first-price auction is not. However, the Bayes--Nash equilibrium is the unique solution to the VI within the class of uniformly increasing bid functions, which ensures that gradient-based algorithms attain the equilibrium in case of convergence, as also observed in numerical experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2311_15398
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle On the Convergence of Learning Algorithms in Bayesian Auction Games
Bichler, Martin
Lunowa, Stephan B.
Oberlechner, Matthias
Pieroth, Fabian R.
Wohlmuth, Barbara
Computer Science and Game Theory
Equilibrium problems in Bayesian auction games can be described as systems of differential equations. Depending on the model assumptions, these equations might be such that we do not have a rigorous mathematical solution theory. The lack of analytical or numerical techniques with guaranteed convergence for the equilibrium problem has plagued the field and limited equilibrium analysis to rather simple auction models such as single-object auctions. Recent advances in equilibrium learning led to algorithms that find equilibrium under a wide variety of model assumptions. We analyze first- and second-price auctions where simple learning algorithms converge to an equilibrium. The equilibrium problem in auctions is equivalent to solving an infinite-dimensional variational inequality (VI). Monotonicity and the Minty condition are the central sufficient conditions for learning algorithms to converge to an equilibrium in such VIs. We show that neither monotonicity nor pseudo- or quasi-monotonicity holds for the respective VIs. The second-price auction's equilibrium is a Minty-type solution, but the first-price auction is not. However, the Bayes--Nash equilibrium is the unique solution to the VI within the class of uniformly increasing bid functions, which ensures that gradient-based algorithms attain the equilibrium in case of convergence, as also observed in numerical experiments.
title On the Convergence of Learning Algorithms in Bayesian Auction Games
topic Computer Science and Game Theory
url https://arxiv.org/abs/2311.15398