A variance‐reduced distributed stochastic momentum algorithm over directed networks
Sign Up to like & getrecommendations! Published in 2025 at "Asian Journal of Control"
DOI: 10.1002/asjc.3775
Abstract: The distributed optimization to minimize a smooth and strongly convex function is considered, in which the function can be described as the finite sum of all local objective functions over directed networks. A variance‐reduced distributed… read more here.
Keywords: variance; momentum; reduced distributed; directed networks ... See more keywords
Variance-Reduced Stochastic Quasi-Newton Methods for Decentralized Learning
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Signal Processing"
DOI: 10.1109/tsp.2023.3240652
Abstract: In this work, we investigate stochastic quasi-Newton methods for minimizing a finite sum of cost functions over a decentralized network. We first develop a general algorithmic framework, in which each node constructs a local, inexact… read more here.
Keywords: quasi newton; stochastic quasi; variance reduced; newton methods ... See more keywords
Variable metric proximal stochastic variance reduced gradient methods for nonconvex nonsmooth optimization
Sign Up to like & getrecommendations! Published in 2021 at "Journal of Industrial and Management Optimization"
DOI: 10.3934/jimo.2021084
Abstract: We study the problem of minimizing the sum of two functions. The first function is the average of a large number of nonconvex component functions and the second function is a convex (possibly nonsmooth) function… read more here.
Keywords: stochastic variance; variance reduced; proximal stochastic; variable metric ... See more keywords