Predictive online convex optimization

Antoine Lesage-Landry, Iman Shames, Joshua A. Taylor

Research output: Contribution to journalArticlepeer-review

13 Scopus citations


We incorporate future information in the form of the estimated value of future gradients in online convex optimization. This is motivated by demand response in power systems, where forecasts about the current round, e.g., the weather or the loads’ behavior, can be used to improve on predictions made with only past observations. Specifically, we introduce an additional predictive step that follows the standard online convex optimization step when certain conditions on the estimated gradient and descent direction are met. We show that under these conditions and without any assumptions on the predictability of the environment, the predictive update strictly improves on the performance of the standard update. We give two types of predictive update for various family of loss functions. We provide a regret bound for each of our predictive online convex optimization algorithms. Finally, we apply our framework to an example based on demand response which demonstrates its superior performance to a standard online convex optimization algorithm.

Original languageEnglish (US)
Article number108771
StatePublished - Mar 2020
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Electrical and Electronic Engineering


  • Convex optimization
  • Learning algorithms
  • Load dispatching
  • Machine learning
  • Power systems
  • Renewable energy systems


Dive into the research topics of 'Predictive online convex optimization'. Together they form a unique fingerprint.

Cite this