Differentiable Economics: Strategic Behavior, Mechanisms, and Machine Learning

Economics studies the behavior of individuals and firms in making decisions regarding the allocation of scarce resources and the interactions among these agents. Game theory had a substantial impact on economic modeling because it allows us to model the outcome of such economic interaction while taking the incentives of individual agents into account. Mechanism design does the same when designing the rules of economic institutions. Unfortunately, these economic models have turned out to be computationally hard to solve. For example, finding equilibrium in some incomplete-information models of markets with continuous valuation and action spaces are hard in PP, and designing a revenue-maximizing multi-item auction is # P -hard. This computational complexity poses a fundamental barrier in modeling economic systems but is worst-case and considers non-generic instances. Differentiable economics describes a new approach to solving these central problems in the economic sciences. It uses learning algorithms to find or approximate solutions to equilibrium computation or economic design problems. In particular, neural networks and learning algorithms such as Stochastic Gradient Descent have been shown to be very effective. Machine learning has led to breakthroughs in many sciences, and it also holds the potential to fundamentally alter how we analyze and design economic systems.