.png){kind=icon}
.png){kind=icon}
Return
Decentralized Asynchronous Nonconvex Stochastic Optimization on Directed Graphs
.png){kind=icon}
OA
AI
DOI：10.1109/TCNS.2023.3242043.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this article, we consider a decentralized stochastic optimization problem over a network of agents, modeled as a directed graph: Agents aim to asynchronously minimize the average of their individual losses (possibly nonconvex), each one having access only to a noisy estimate of the gradient of its own function. We propose an asynchronous distributed algorithm for such a class of problems. The algorithm combines stochastic gradients with tracking in an asynchronous push-sum framework and obtains a sublinear convergence rate, matching the rate of the centralized stochastic gradient descent applied to the nonconvex minimization. Our experiments on a nonconvex image classification task using a convolutional neural network validate the convergence of our proposed algorithm across a different number of nodes and graph connectivity percentages.
Keywords:
Optimization
Stochastic processes
Convergence
Delays
Directed graphs
Noise measurement
Linear programming
Decentralized applications
distributed computing
federated learning
machine learning
optimization
optimization methods
Journal
IF:
5
Papers:
1.6K
Citations:
5.8K
Organization
View more organizations