Local updates accelerate the DIGing algorithm in distributed optimization, with maximal gains from two updates that depend on network spectral properties.
Guaranteeing both consens us and optimality in decentralized nonconvex optimization with m ultiple local updates
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
AdaDQN is a decentralized quasi-Newton algorithm with safeguarded local updates, memoryless BFGS, and event-triggered communication that converges globally to first-order stationary points with stepsize independent of the maximum number of local updates.
citing papers explorer
-
Local Updates in Distributed Optimization: Provable Acceleration and Topology Effects
Local updates accelerate the DIGing algorithm in distributed optimization, with maximal gains from two updates that depend on network spectral properties.
-
Beyond Fixed Local Updates: An Adaptive Decentralized Quasi-Newton Method Free of Stepsize Degradation
AdaDQN is a decentralized quasi-Newton algorithm with safeguarded local updates, memoryless BFGS, and event-triggered communication that converges globally to first-order stationary points with stepsize independent of the maximum number of local updates.