Efficient first order method for saddle point problems with higher order smoothness

DOI10.1137/23M1566972MaRDI QIDQ6622754zbMATH OpenFDO

Authors Nuozhou Wang, Junyu Zhang, Shuzhong Zhang

Publication date 22 October 2024

Published in SIAM Journal on Optimization (Search for Journal in Brave)

zbMATH Keywords

iteration complexityfirst-order methodnonconvex-concave minimax problem

Mathematics Subject Classification ID

Analysis of algorithms and problem complexity (68Q25) Nonconvex programming, global optimization (90C26) Minimax problems in mathematical programming (90C47)

Recommendations

• Lower complexity bounds of first-order methods for convex-concave bilinear saddle-point problems
• On lower iteration complexity bounds for the convex concave saddle point problems
• Higher-order methods for convex-concave min-max optimization and monotone variational inequalities
• Lower bounds for finding stationary points II: first-order methods
• Efficient search of first-order Nash equilibria in nonconvex-concave smooth min-max problems

Cites work

• A \(J\)-symmetric quasi-Newton method for minimax problems
• Accelerated methods for nonconvex optimization
• Alternating Proximal-Gradient Steps for (Stochastic) Nonconvex-Concave Minimax Problems
• An Accelerated Inexact Proximal Point Method for Solving Nonconvex-Concave Min-Max Problems
• Cubic regularization of Newton method and its global performance
• Cubic regularized Newton method for the saddle point models: a global and local convergence analysis
• Higher-order methods for convex-concave min-max optimization and monotone variational inequalities
• Hybrid Block Successive Approximation for One-Sided Non-Convex Min-Max Problems: Algorithms and Applications
• Katyusha: the first direct acceleration of stochastic gradient methods
• Lectures on convex optimization
• Lower bounds for finding stationary points I
• Lower bounds for finding stationary points II: first-order methods
• Monotone Inclusions, Acceleration, and Closed-Loop Control
• Primal-Dual First-Order Methods for Affinely Constrained Multi-block Saddle Point Problems
• The Fitting of Power Series, Meaning Polynomials, Illustrated on Band-Spectroscopic Data
• Worst-case evaluation complexity for unconstrained nonlinear optimization using high-order regularized models

This page was built for publication: Efficient first order method for saddle point problems with higher order smoothness

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6622754)