MultiLRSGA extends the two-player LRSGA method to multiple players by constructing per-player low-rank Jacobian approximations to define an approximate block antisymmetric correction, and proves local linear convergence to stable Nash equilibria under standard local assumptions.
Differentiable game mechanics.Journal of Machine Learning Research, 20(84):1–40
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
-
MultiLRSGA: A method for multi-player differentiable games
MultiLRSGA extends the two-player LRSGA method to multiple players by constructing per-player low-rank Jacobian approximations to define an approximate block antisymmetric correction, and proves local linear convergence to stable Nash equilibria under standard local assumptions.