Skip to main content

Prediction in Online Convex Optimization for Parametrizable Objective Functions

Publication ,  Journal Article
Ravier, RJ; Calderbank, AR; Tarokh, V
Published in: Proceedings of the IEEE Conference on Decision and Control
December 1, 2019

Many techniques for online optimization problems involve making decisions based solely on presently available information: fewer works take advantage of potential predictions. In this paper, we discuss the problem of online convex optimization for parametrizable objectives, i.e. optimization problems that depend solely on the value of a parameter at a given time. We introduce a new regularity for dynamic regret based on the accuracy of predicted values of the parameters and show that, under mild assumptions, accurate prediction can yield tighter bounds on dynamic regret. Inspired by recent advances on learning how to optimize, we also propose a novel algorithm to simultaneously predict and optimize for parametrizable objectives and study its performance using numerical experiments.

Duke Scholars

Published In

Proceedings of the IEEE Conference on Decision and Control

DOI

EISSN

2576-2370

ISSN

0743-1546

Publication Date

December 1, 2019

Volume

2019-December

Start / End Page

2455 / 2460
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Ravier, R. J., Calderbank, A. R., & Tarokh, V. (2019). Prediction in Online Convex Optimization for Parametrizable Objective Functions. Proceedings of the IEEE Conference on Decision and Control, 2019-December, 2455–2460. https://doi.org/10.1109/CDC40024.2019.9030013
Ravier, R. J., A. R. Calderbank, and V. Tarokh. “Prediction in Online Convex Optimization for Parametrizable Objective Functions.” Proceedings of the IEEE Conference on Decision and Control 2019-December (December 1, 2019): 2455–60. https://doi.org/10.1109/CDC40024.2019.9030013.
Ravier RJ, Calderbank AR, Tarokh V. Prediction in Online Convex Optimization for Parametrizable Objective Functions. Proceedings of the IEEE Conference on Decision and Control. 2019 Dec 1;2019-December:2455–60.
Ravier, R. J., et al. “Prediction in Online Convex Optimization for Parametrizable Objective Functions.” Proceedings of the IEEE Conference on Decision and Control, vol. 2019-December, Dec. 2019, pp. 2455–60. Scopus, doi:10.1109/CDC40024.2019.9030013.
Ravier RJ, Calderbank AR, Tarokh V. Prediction in Online Convex Optimization for Parametrizable Objective Functions. Proceedings of the IEEE Conference on Decision and Control. 2019 Dec 1;2019-December:2455–2460.

Published In

Proceedings of the IEEE Conference on Decision and Control

DOI

EISSN

2576-2370

ISSN

0743-1546

Publication Date

December 1, 2019

Volume

2019-December

Start / End Page

2455 / 2460