Log-barrier regularization in online mirror descent attains the optimal Õ(t^{-1/4}) last-iterate convergence rate in uncoupled zero-sum matrix games under bandit feedback.
Faster first-order methods for extensive-form game solving
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Optimal last-iterate convergence in matrix games with bandit feedback using the log-barrier
Log-barrier regularization in online mirror descent attains the optimal Õ(t^{-1/4}) last-iterate convergence rate in uncoupled zero-sum matrix games under bandit feedback.