PALM achieves Õ(ε^{-1}) first-order complexity for ε-KKT points in convex-strongly-concave minimax problems with functional constraints and Õ(ε^{-3/2}) for the dual in the convex-concave case.
arXiv preprint arXiv:2502.17602 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
math.OC 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Develops robust SGLD with non-asymptotic convergence bounds for non-convex DRO and applies it to neural network regression under adversarial corruption.
citing papers explorer
-
First-Order Methods for Solving Convex (Strongly) Concave Minimax Problems with Functional Constraints
PALM achieves Õ(ε^{-1}) first-order complexity for ε-KKT points in convex-strongly-concave minimax problems with functional constraints and Õ(ε^{-3/2}) for the dual in the convex-concave case.
-
Robust SGLD algorithm for solving non-convex distributionally robust optimisation problems
Develops robust SGLD with non-asymptotic convergence bounds for non-convex DRO and applies it to neural network regression under adversarial corruption.