Strategic Prediction with Latent Aggregative Games

Abstract

We introduce a new class of context dependent, incomplete information games to serve as structured prediction models for settings with significant strategic interactions. Our games map the input context to outcomes by first condensing the input into private player types that specify the utilities, weighted interactions, as well as the initial strategies for the players. The game is played over multiple rounds where players respond to weighted aggregates of their neighbors' strategies. The predicted output from the model is a mixed strategy profile (a near-Nash equilibrium) and each observation is thought of as a sample from this strategy profile. We introduce two new aggregator paradigms with provably convergent game dynamics, and characterize the conditions under which our games are identifiable from data. Our games can be parameterized in a transferable manner so that the sets of players can change from one game to another. We demonstrate empirically that our games as models can recover meaningful strategic interactions from real voting data.

References in corpus (9)

• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Graphical Models for Game Theory
• The Numerics of GANs
• Efficient Nash Computation in Large Population Games with Bounded Influence
• On Influence, Stable Behavior, and the Most Influential Individuals in Networks: A Game-Theoretic Approach
• Structured Prediction Theory Based on Factor Graph Complexity
• Learning the Structure and Parameters of Large-Population Graphical Games from Behavioral Data
• On Structured Prediction Theory with Calibrated Convex Surrogate Losses
• Learning Graphical Games from Behavioral Data: Sufficient and Necessary Conditions