For bilinear zero-sum games, the paper derives necessary and sufficient convergence conditions and optimal linear rates for generalized GD, EG, OGD, and momentum methods, with Gauss-Seidel updates converging in a larger region than Jacobi updates.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Convergence of Gradient Methods on Bilinear Zero-Sum Games
For bilinear zero-sum games, the paper derives necessary and sufficient convergence conditions and optimal linear rates for generalized GD, EG, OGD, and momentum methods, with Gauss-Seidel updates converging in a larger region than Jacobi updates.