Stochastic Push-Pull achieves linear speedup, O(1/(nε^2)) iteration complexity, over arbitrary strongly connected digraphs in the nonconvex setting.
Communication- efficient topologies for decentralized learning witho(1) consensus rate.Advances in Neural Information Processing Systems, 35:1073–1085, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
On the Linear Speedup of the Push-Pull Method for Decentralized Optimization over Digraphs
Stochastic Push-Pull achieves linear speedup, O(1/(nε^2)) iteration complexity, over arbitrary strongly connected digraphs in the nonconvex setting.