Asynchronous decentralized accelerated stochastic gradient descent
Abstract
In this work, we introduce an asynchronous decentralized accelerated stochastic gradient descent type of method for decentralized stochastic optimization, considering communication and synchronization are the major bottlenecks. We establish O(1/ε) (resp., O(1/ε)) communication complexity and O(1/ε2) (resp., O(1/ε)) sampling complexity for solving general convex (resp., strongly convex) problems.
0
Turn this paper into a lesson
ArcXiv compiles a structured reading guide from this paper's metadata: plain-English importance, contributions, prerequisite concepts, which sections to read first, flashcards, and a quiz. Grounded in the abstract, never invented.