A momentum-augmented local decentralized method achieves O(κ ε^{-1}) local updates per round and O(κ² ε^{-2}) communication complexity for nonconvex PL minimax problems, improving on prior local GDA.
On the influence of bias-correction on distributed stochas- tic optimization,
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
-
Communication-Efficient Decentralized Stochastic Minimax Optimization
A momentum-augmented local decentralized method achieves O(κ ε^{-1}) local updates per round and O(κ² ε^{-2}) communication complexity for nonconvex PL minimax problems, improving on prior local GDA.