A Learning Framework for Distribution-Based Game-Theoretic Solution Concepts

The past few years have seen several works exploring learning economic solutions from data, including optimal auction design, function optimization, stable payoffs in cooperative games, and more. In this work, we provide a unified learning-theoretic methodology for modeling such problems and establish tools for determining whether a given solution concept can be efficiently learned from data. Our learning-theoretic framework generalizes a notion of function space dimension—the graph dimension—adapting it to the solution concept learning domain. We identify sufficient conditions for efficient solution learnability and show that results in existing works can be immediately derived using our methodology. Finally, we apply our methods in other economic domains, yielding learning variants of competitive equilibria and Condorcet winners.