Vanilla SGD achieves O(log(t)/t^{1/3}) last-iterate convergence to Nash equilibria in co-coercive games under affine noise scaling, plus almost-sure and time-average convergence.
On the rate of convergence of payoff-based algorithms to nash equilibrium in strongly monotone games
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
In bandit-feedback zero-sum games, uncoupled algorithms achieve last-iterate Nash convergence at the optimal rate of O(T^{-1/4}).
citing papers explorer
-
Last-Iterate Guarantees for Learning in Co-coercive Games
Vanilla SGD achieves O(log(t)/t^{1/3}) last-iterate convergence to Nash equilibria in co-coercive games under affine noise scaling, plus almost-sure and time-average convergence.
-
The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback
In bandit-feedback zero-sum games, uncoupled algorithms achieve last-iterate Nash convergence at the optimal rate of O(T^{-1/4}).