New trust-region and Levenberg-Marquardt algorithms for nonconvex-strongly concave minimax problems achieve the best known outer complexity and improve Hessian-vector product complexity to O(epsilon^-1.75).
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Gradient Norm Regularization Second-Order Algorithms for Solving Nonconvex-Strongly Concave Minimax Problems
New trust-region and Levenberg-Marquardt algorithms for nonconvex-strongly concave minimax problems achieve the best known outer complexity and improve Hessian-vector product complexity to O(epsilon^-1.75).