A new symmetric accelerated ADMM is introduced with convergence and iteration-complexity analysis for nonconvex problems, tested on sparse signal processing minimization.
Convergence rate bounds for a proximal ADMM with over-relaxation stepsize parameter for solving nonconvex linearly constrained problems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
This paper establishes convergence rate bounds for a variant of the proximal alternating direction method of multipliers (ADMM) for solving nonconvex linearly constrained optimization problems. The variant of the proximal ADMM allows the inclusion of an over-relaxation stepsize parameter belonging to the interval $(0,2)$. To the best of our knowledge, all related papers in the literature only consider the case where the over-relaxation parameter lies in the interval $(0,(1+\sqrt{5})/2)$.
fields
math.NA 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Accelerated Symmetric ADMM and Its Applications in Signal Processing
A new symmetric accelerated ADMM is introduced with convergence and iteration-complexity analysis for nonconvex problems, tested on sparse signal processing minimization.