Establishes Riemannian metrics that define contraction regions for primal-dual gradient dynamics, yielding convergence rates for equality-constrained and augmented-Lagrangian inequality-constrained convex problems under suitable step-size choices.
On the linear convergence of the ADMM in decentralized consensus optimiz ation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Contraction Analysis on Primal-Dual Gradient Optimization
Establishes Riemannian metrics that define contraction regions for primal-dual gradient dynamics, yielding convergence rates for equality-constrained and augmented-Lagrangian inequality-constrained convex problems under suitable step-size choices.