The Dual² approach produces iD2A and MiD2A gradient methods that achieve asymptotic convergence under milder conditions on the public function and linear rates with reduced communication and computation complexity.
Dual acceleration for minimax optimization: Linear convergence under relaxed assumptions,
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
-
Accelerated Decentralized Constraint-Coupled Optimization: A Dual$^2$ Approach
The Dual² approach produces iD2A and MiD2A gradient methods that achieve asymptotic convergence under milder conditions on the public function and linear rates with reduced communication and computation complexity.