A quasi-Newton subspace trust region algorithm for nonmonotone variational inequalities in adversarial learning over box constraints

DOI10.1007/S10915-024-02679-YMaRDI QIDQ6629223zbMATH OpenFDO

Authors Zicheng Qiu, Jie Jiang, Xiaojun Chen

Publication date 29 October 2024

Published in Journal of Scientific Computing (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1007/S10915-024-02679-Y

zbMATH Keywords

generative adversarial networksleast squares problemmin-max optimizationnonmonotone variational inequalityquasi-Newton method

Mathematics Subject Classification ID

Numerical methods for variational inequalities and related problems (65K15) Stochastic programming (90C15) Complementarity and equilibrium problems and variational inequalities (finite dimensions) (aspects of mathematical programming) (90C33) Minimax problems in mathematical programming (90C47)

Recommendations

• A globally and superlinearly convergent quasi-Newton method for general box constrained variational inequalities without smoothing approximation
• Weakly-convex-concave min-max optimization: provable algorithms and applications in machine learning
• Optimality Conditions for Nonsmooth Nonconvex-Nonconcave Min-Max Problems and Generative Adversarial Networks
• First-order convergence theory for weakly-convex-weakly-concave min-max problems
• A J-symmetric quasi-Newton method for minimax problems

Cites work

• Approximate Gauss–Newton Methods for Nonlinear Least Squares Problems
• Complexity of Variants of Tseng's Modified F-B Splitting and Korpelevich's Methods for Hemivariational Inequalities with Applications to Saddle-point and Convex Optimization Problems
• Computer vision. Algorithms and applications
• Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
• Dual extrapolation and its applications to solving variational inequalities and related problems
• Finite-Dimensional Variational Inequalities and Complementarity Problems
• First-order convergence theory for weakly-convex-weakly-concave min-max problems
• Global and superlinear convergence of the smoothing Newton method and its application to general box constrained variational inequalities
• Global convergence of a new hybrid Gauss-Newton structured BFGS method for nonlinear least squares problems
• scientific article; zbMATH DE number 3928227 (Why is no real title available?)
• scientific article; zbMATH DE number 49749 (Why is no real title available?)
• scientific article; zbMATH DE number 2121076 (Why is no real title available?)
• Lectures on stochastic programming. Modeling and theory
• Optimality Conditions for Nonsmooth Nonconvex-Nonconcave Min-Max Problems and Generative Adversarial Networks
• Optimization and nonsmooth analysis
• Prox-Method with Rate of Convergence O(1/t) for Variational Inequalities with Lipschitz Continuous Monotone Operators and Smooth Convex-Concave Saddle Point Problems
• Recent advances in trust region algorithms
• Superlinear convergence of smoothing quasi-Newton methods for nonsmooth equations
• Trust Region Methods
• Uniform exponential convergence of sample average random functions under general sampling with applications in stochastic programming
• Weakly-convex-concave min-max optimization: provable algorithms and applications in machine learning

Cited in

(1)

• Step function based light Newton-like method for AUC

This page was built for publication: A quasi-Newton subspace trust region algorithm for nonmonotone variational inequalities in adversarial learning over box constraints

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6629223)