SMTPP decouples variance reduction from graph connectivity in push-pull decentralized optimization and guarantees convergence with a compressed steady-state error floor on any strongly connected directed graph.
A linear algorithm for optimization over directed graphs with geometric convergence,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Stochastic Momentum Tracking Push-Pull for Decentralized Optimization over Directed Graphs
SMTPP decouples variance reduction from graph connectivity in push-pull decentralized optimization and guarantees convergence with a compressed steady-state error floor on any strongly connected directed graph.