The past few years have seen several works on learning economic solutions from data; these include 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 economic solution concept can be 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 the PAC learnability of solution concepts, and show that results in existing works can be immediately derived using our methodology. Finally, we apply our methods in other economic domains, yielding a novel notion of PAC competitive equilibrium and PAC Condorcet winners.
Neural Concept Verifier: Scaling Prover-Verifier Games via Concept Encodings
Zuse Institute Berlin, Germany;AI \& ML Lab, Computer Science Department, TU Darmstadt;Hessian Center for AI (hessian.AI);Lab1141;German Research Center for AI (DFKI);Institute of Mathematics, Technische Universit\"at Berlin, Germany;Max Planck Institute for Informatics, SIC
Interactive Language Acquisition with One-shot Visual Concept Learning through a Conversational Game
Baidu Research - Institue of Deep Learning(百度研究院 - 深度学习研究所);National Engineering Laboratory for Deep Learning Technology and Applications(深度学习技术及应用国家工程实验室)