We study the stochastic first-order oracle complexity of finding $\epsilon$-stationary points of the primal function in smooth nonconvex-strongly-concave minimax optimization. For sufficiently small $\epsilon$, we establish lower bounds of $\Omega(\kappa L\Delta\sigma^2\epsilon^{-4})$ under the bounded-variance assumpt...
We study lower bounds on the first-order oracle complexity of smooth nonconvex-concave minimax optimization. We consider objectives $f$ that are jointly $L$-smooth in the primal and dual variables $(x,y)$, concave in $y$, and whose primal value function $\Phi(x) := \max_{y\in\mathcal Y} f(x,y)$ satisfies the initial-ga...
This work proposes a novel single-loop algorithm based on a constrained reformulation in which lower-level stationarity is imposed as a constraint, and constructs a regularized Lagrangian by introducing a quadratic regularizer and restricting the dual variable to a bounded domain.