Adaptive Composite Online Optimization

Predictions in Static and Dynamic Environments

Journal Article (2023)
Author(s)

Pedro Zattoni Zattoni Scroccaro (TU Delft - Team Peyman Mohajerin Esfahani)

A. Sharifi Kolarijani (TU Delft - Team Tamas Keviczky)

P. Mohajerin Esfahani (TU Delft - Team Peyman Mohajerin Esfahani)

Research Group
Team Peyman Mohajerin Esfahani
Copyright
© 2023 P. Zattoni Scroccaro, Arman Sharifi K., P. Mohajerin Esfahani
DOI related publication
https://doi.org/10.1109/TAC.2023.3237486
More Info
expand_more
Publication Year
2023
Language
English
Copyright
© 2023 P. Zattoni Scroccaro, Arman Sharifi K., P. Mohajerin Esfahani
Research Group
Team Peyman Mohajerin Esfahani
Issue number
5
Volume number
68
Pages (from-to)
2906-2921
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

In the past few years, online convex optimization (OCO) has received notable attention in the control literature thanks to its flexible real-time nature and powerful performance guarantees. In this article, we propose new step-size rules and OCO algorithms that simultaneously exploit gradient predictions, function predictions and dynamics, features particularly pertinent to control applications. The proposed algorithms enjoy static and dynamic regret bounds in terms of the dynamics of the reference action sequence, gradient prediction error, and function prediction error, which are generalizations of known regularity measures from the literature. We present results for both convex and strongly convex costs. We validate the performance of the proposed algorithms in a trajectory tracking case study, as well as portfolio optimization using real-world datasets.

Files

Adaptive_Composite_Online_Opti... (pdf)
(pdf | 1.32 Mb)
- Embargo expired in 16-07-2023
License info not available