A local backtracking rule for stepsizes in decentralized composite convex optimization is shown to preserve robust convergence without global network information.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Parameter-free Decentralized Algorithm for Composite Convex Optimization
A local backtracking rule for stepsizes in decentralized composite convex optimization is shown to preserve robust convergence without global network information.