A Quasi-Newton Subspace Trust Region Algorithm for Nonmonotone Variational Inequalities in Adversarial Learning over Box Constraints
Open Access
- 5 October 2024
- journal article
- research article
- Published by Springer Nature in Journal of Scientific Computing
- Vol. 101 (2) , 1-30
Abstract
The first-order optimality condition of convexly constrained nonconvex nonconcave min-max optimization problems with box constraints formulates a nonmonotone variational inequality (VI), which is equivalent to a system of nonsmooth equations. In this paper, we propose a quasi-Newton subspace trust region (QNSTR) algorithm for the least squares problems defined by the smoothing approximation of nonsmooth equations. Based on the structure of the nonmonotone VI, we use an adaptive quasi-Newton formula to approximate the Hessian matrix and solve a low-dimensional strongly convex quadratic program with ellipse constraints in a subspace at each step of the QNSTR algorithm efficiently. We prove the global convergence of the QNSTR algorithm to an $$\epsilon $$ -first-order stationary point of the min-max optimization problem. Moreover, we present numerical results based on the QNSTR algorithm with different subspaces for a mixed generative adversarial networks in eye image segmentation using real data to show the efficiency and effectiveness of the QNSTR algorithm for solving large-scale min-max optimization problems.
Keywords
All Related Versions
Funding Information
- Hong Kong Polytechnic University (15300021)
This publication has 29 references indexed in Scilit:
- Computer Vision2022
- DUNet: A deformable network for retinal vessel segmentationKnowledge-Based Systems, 2019
- Towards Accurate Segmentation of Retinal Vessels and the Optic Disc in Fundoscopic Images with Generative Adversarial NetworksJournal of Digital Imaging, 2018
- Deep Adversarial Networks for Biomedical Image Segmentation Utilizing Unannotated Images2017
- Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulationsMathematical Programming, 2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Recent advances in trust region algorithmsMathematical Programming, 2015
- Uniform exponential convergence of sample average random functions under general sampling with applications in stochastic programmingJournal of Mathematical Analysis and Applications, 2010
- Dual extrapolation and its applications to solving variational inequalities and related problemsMathematical Programming, 2006
- The use of the area under the ROC curve in the evaluation of machine learning algorithmsPattern Recognition, 1997