Towards a Blend of Machine Learning and Microeconomics

Michael I. Jordan, University of California, Berkeley

Statistical decisions are often given meaning in the context of other decisions, particularly when there are scarce resources to be shared. Managing such sharing is one of the classical goals of microeconomics, and it is given new scope in the modern setting of large, human-focused datasets, and in data-analytic contexts such as classifiers and recommendation systems. I'll discuss several recent projects that aim to explore this interface: (1) exploration-exploitation tradeoffs for bandits that compete over a scarce resource; (2) Langevin diffusions for solving Thompson sampling problems; and (3) economic perspectives on online control of false-discovery rates.