Online convex programming and regularization in adaptive control

Online Convex Programming (OCP) is a recently developed model of sequential decision-making in the presence of time-varying uncertainty. In this framework, a decision-maker selects points in a convex feasible set to respond to a dynamically changing sequence of convex cost functions. A generic algorithm for OCP, often with provably optimal performance guarantees, is inspired by the Method of Mirror Descent (MD) developed by Nemirovski and Yudin in the 1970's. This paper highlights OCP as a common theme in adaptive control, both in its classical variant based on parameter tuning and in a more modern supervisory approach. Specifically, we show that: (1) MD leads to a generalization of classical adaptive control schemes based on recursive parameter tuning; (2) A supervisory controller switching policy that uses OCP to estimate system parameters from a sequence of appropriately regularized output prediction errors can flexibly adapt to presence or absence of output disturbances in the system.