Achieving acceleration in distributed optimization via direct discretization of the heavy-ball ODE

Achieving acceleration in distributed optimization via direct discretization of the heavy-ball ODE

© 2019 American Automatic Control Council. We develop a distributed algorithm for convex Empirical Risk Minimization, the problem of minimizing large but finite sum of convex functions over networks. The proposed algorithm is derived from directly discretizing the second-order heavy-ball differentia...

Celý popis

Podrobná bibliografie
Hlavní autoři: Zhang, J, Uribe, CA, Mokhtari, A, Jadbabaie, A
Další autoři: Massachusetts Institute of Technology. Department of Civil and Environmental Engineering
Médium: Článek
Jazyk:English
Vydáno: IEEE 2023
On-line přístup:https://hdl.handle.net/1721.1/148596

Internet

https://hdl.handle.net/1721.1/148596

Podobné jednotky