Message Passing Algorithms for Graphical Games

An Empirical Evaluation of Algorithms for Computing Equilibria in Games for Approximate Inference in Large Dimensional Probabilistic Graphical Models

Work in graphical models for game theory typically borrows from results in probabilistic graphical models. In this work, we instead consider the opposite direction. By using recent advances in equilibrium computation, we propose game-theoretic inspired, practical methods to perform probabilistic inference. We perform synthetic experiments using several different classes of Ising models, in orde...

Graphical models and message-passing algorithms for network-constrained decision problems

3

Statistical mechanics, graphical models and message passing algorithms

Message passing algorithms and analog electronic circuits

Solving decision problems by means of message-passing algorithms defined on graphical models has received increasing attention in recent years. The origin of this approach lies in coding theory and can be traced back to work by Gallager in 1963 and Tanner in 1981. The actual breakthrough though was marked by the discovery of turbo codes in 1993, coinciding with advances by Wiberg in graphical m...

Nash Propagation for Loopy Graphical Games

We introduce NashProp, an iterative and local message-passing algorithm for computing Nash equilibria in multi-player games represented by arbitrary undirected graphs. We provide a formal analysis and experimental evidence demonstrating that NashProp performs well on large graphical games with many loops, often converging in just a dozen iterations on graphs with hundreds of nodes. NashProp gen...