A momentum variant of the Exact-Diffusion decentralized algorithm is shown to converge sublinearly for nonconvex objectives and linearly under the PL condition, with convergence error independent of data heterogeneity.
Title resolution pending
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
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
A Bias-Correction Decentralized Stochastic Gradient Algorithm with Momentum Acceleration
A momentum variant of the Exact-Diffusion decentralized algorithm is shown to converge sublinearly for nonconvex objectives and linearly under the PL condition, with convergence error independent of data heterogeneity.