A unified framework for decentralized nonconvex optimization that encompasses gradient tracking and quasi-Newton methods, with convergence analysis under nonconvex and Kurdyka-Lojasiewicz conditions and new efficient algorithms.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Unified Algorithm for Nonconvex Decentralized Nonlinear Optimization
A unified framework for decentralized nonconvex optimization that encompasses gradient tracking and quasi-Newton methods, with convergence analysis under nonconvex and Kurdyka-Lojasiewicz conditions and new efficient algorithms.