A novel decoupled method for distributed saddle problems achieves optimal communication complexity via multi-stage residual norm minimization, with a matching lower bound and extension to variational inequalities.
Proceedings of the twenty-first international conference on Machine learning , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Efficient Gradient Methods for Distributed Saddle Problems
A novel decoupled method for distributed saddle problems achieves optimal communication complexity via multi-stage residual norm minimization, with a matching lower bound and extension to variational inequalities.