Adaptive Composite Online Optimization

Adaptive Composite Online Optimization: Predictions in Static and Dynamic Environments

Zattoni Scroccaro, P. (TU Delft Team Peyman Mohajerin Esfahani)
Sharifi K., Arman (TU Delft Team Tamas Keviczky)
Mohajerin Esfahani, P. (TU Delft Team Peyman Mohajerin Esfahani)

2023

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.

composite costs
Convex functions
Costs
dynamic environments
Heuristic algorithms
Mirrors
Online convex optimization
Prediction algorithms
predictions
Predictive models
real-time control
Standards

http://resolver.tudelft.nl/uuid:ada86683-0518-4441-ac76-95124abbed87

https://doi.org/10.1109/TAC.2023.3237486

2023-07-16

0018-9286

IEEE Transactions on Automatic Control, 68 (5), 2906-2921

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Institutional Repository

journal article

© 2023 P. Zattoni Scroccaro, Arman Sharifi K., P. Mohajerin Esfahani