Abstract | ||
---|---|---|
In this paper, we introduce an asynchronous decentralized accelerated stochastic gradient descent type of algorithm for decentralized stochastic optimization. Considering communication and synchronization costs are the major bottlenecks for decentralized optimization, we attempt to reduce these costs from an algorithmic design aspect, in particular, we are able to reduce the number of agents invol... |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/JSAIT.2021.3080256 | IEEE Journal on Selected Areas in Information Theory |
Keywords | Field | DocType |
Complexity theory,Convergence,Signal processing algorithms,Optimization,Delays,Support vector machines,Convex functions | Discrete mathematics,Asynchronous communication,Stochastic gradient descent,Stochastic optimization,Synchronization,Regular polygon,Communication complexity,Convex function,Sampling (statistics),Mathematics | Journal |
Volume | Issue | Citations |
2 | 2 | 0 |
PageRank | References | Authors |
0.34 | 0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Guanghui Lan | 1 | 1212 | 66.26 |
yi zhou | 2 | 88 | 5.26 |