A Penalty-Based Method for Communication-Efficient Decentralized Bilevel Programming

Bilevel programming has recently received attention in the literature due to its wide range of applications, including reinforcement learning and hyper-parameter optimization. However, it is widely assumed that the underlying bilevel optimization problem is solved either by a single machine or, in t...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-10
Hauptverfasser:	Nazari, Parvin, Mousavi, Ahmad, Davoud Ataee Tarzanagh, Michailidis, George
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Communication Convergence Convexity Empirical analysis Machine learning Mathematical analysis Minimax technique Optimization Parameters Penalty function Programming
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!