New adaptive decentralized algorithms select stepsizes from local curvature estimates derived from a Lyapunov function, delivering sublinear convergence for convex problems and linear rates for strongly convex ones.
Achieving geometric conver- gence for distributed optimization over time-varying graphs,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
math.OC 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
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.
citing papers explorer
-
A Line-search-free Method for Adaptive Decentralized Optimization
New adaptive decentralized algorithms select stepsizes from local curvature estimates derived from a Lyapunov function, delivering sublinear convergence for convex problems and linear rates for strongly convex ones.
-
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.