Unified analysis shows decentralized ProxSkip achieves linear speedup in number of nodes under stochastic gradients for non-convex problems.
A unified and refined convergence analysis for non-convex decentralized learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Achieving Linear Speedup with ProxSkip in Distributed Stochastic Optimization
Unified analysis shows decentralized ProxSkip achieves linear speedup in number of nodes under stochastic gradients for non-convex problems.