Byzantine-Robust Decentralized Federated Learning
Minghong Fang, Zifan Zhang, et al.
CCS 2024
We consider the global and local convergence properties of a class of Lagrangian barrier methods for solving nonlinear programming problems. In such methods, simple bound constraints may be treated separately from more general constraints. The objective and general constraint functions are combined in a Lagrangian barrier function. A sequence of such functions are approximately minimized within the domain defined by the simple bounds. Global convergence of the sequence of generated iterates to a first-order stationary point for the original problem is established. Furthermore, possible numerical difficulties associated with barrier function methods are avoided as it is shown that a potentially troublesome penalty parameter is bounded away from zero. This paper is a companion to previous work of ours on augmented Lagrangian methods.
Minghong Fang, Zifan Zhang, et al.
CCS 2024
Ligang Lu, Jack L. Kouloheris
IS&T/SPIE Electronic Imaging 2002
J. LaRue, C. Ting
Proceedings of SPIE 1989
Chai Wah Wu
Linear Algebra and Its Applications