A Family of Distributed Momentum Methods Over Directed Graphs With ...
ieeexplore.ieee.org › document
Mar 18, 2022 · We propose a family of distributed momentum methods. It is a parametric distributed momentum (PDM) method, for which different values of parameter can lead to ...
Acc-DNGD is proved to have a linear convergence rate for smooth and strongly convex functions. Based on accelerated penalty methods with increasing penalty.
Oct 22, 2024 · We consider the distributed optimization to minimize a sum of smooth and strongly convex local objective functions over directed graphs.
This paper proposes two accelerated algorithms, named DSGT-HB andDSGT-NAG, which combine the distributed stochastic gradient tracking method with momentum ...
This paper studies a distributed aggregative optimization problem over a directed graph with the row-stochastic weighted matrix.
Missing: Family | Show results with:Family
Oct 28, 2024 · We propose a distributed optimization method based on a unified momentum method combined with the heavy ball method and optimized gradient ...
We introduce a distributed algorithm, referred to as DIGing, based on a combination of a distributed inexact gradient method and a gradient tracking technique.
Oct 22, 2024 · A Family of Distributed Momentum Methods Over Directed Graphs With Linear Convergence. Article. Jan 2022. Juan Gao · X.W. LIU ...
Dec 27, 2024 · The study introduces a novel and effective optimization technique, achieving linear convergence rates through carefully designed methods. This ...
6 Excerpts. A Family of Distributed Momentum Methods Over Directed Graphs With Linear Convergence · Juan GaoXinwei LiuYuhong DaiYakui HuangPeng Yang.