Online Convex Optimization With Binary Constraints

We consider online optimization with binary decision variables and convex loss functions. We design a new algorithm, binary online gradient descent ( bOGD ) and bound its expected dynamic regret. We provide a regret bound that holds for any time horizon and a specialized bound for finite time horizo...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on automatic control 2021-12, Vol.66 (12), p.6164-6170
Hauptverfasser:	Lesage-Landry, Antoine, Taylor, Joshua A., Callaway, Duncan S.
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Binary decision Computational geometry Constraint modelling Convex functions Convexity Decision theory Demand response dynamic regret online convex optimization Optimization Performance degradation Rounding thermostatically controlled loads Tracking errors
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!