Online convex programming and regularization in adaptive control

Maxim Raginsky, Alexander Rakhlin, Serdar Yüksel

Research output: Chapter in Book/Report/Conference proceedingConference contribution


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.

Original languageEnglish (US)
Title of host publication2010 49th IEEE Conference on Decision and Control, CDC 2010
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages6
ISBN (Print)9781424477456
StatePublished - 2010
Externally publishedYes
Event49th IEEE Conference on Decision and Control, CDC 2010 - Atlanta, United States
Duration: Dec 15 2010Dec 17 2010

Publication series

NameProceedings of the IEEE Conference on Decision and Control
ISSN (Print)0743-1546
ISSN (Electronic)2576-2370


Conference49th IEEE Conference on Decision and Control, CDC 2010
Country/TerritoryUnited States

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Modeling and Simulation
  • Control and Optimization


Dive into the research topics of 'Online convex programming and regularization in adaptive control'. Together they form a unique fingerprint.

Cite this