Step function based light Newton-like method for AUC

DOI10.1007/S10915-025-03013-WMaRDI QIDQ6938709zbMATH OpenFDO

Authors Hui Zhang, Zijian Yu, Naihua Xiu, Yiju Wang

Publication date 25 August 2025

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

Full work available at URL https://doi.org/10.1007/S10915-025-03013-W

zbMATH Keywords

\(l_{0/1}\)-AUCNewton-like methodoptimality theorystep function

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Nonlinear programming (90C30)

Cites work

• A Lagrange-Newton algorithm for sparse nonlinear programming
• A quasi-Newton subspace trust region algorithm for nonmonotone variational inequalities in adversarial learning over box constraints
• A step function based recursion method for 0/1 deep neural networks
• An extension of the receiver operating characteristic curve and AUC-optimal classification
• Just least squares: binary compressive sampling with low generative intrinsic dimension
• Quadratic Convergence of Smoothing Newton's Method for 0/1 Loss Optimization
• Robust pairwise learning with Huber loss
• Single-loop projection-free and projected gradient-based algorithms for nonconvex-concave saddle point problems with bilevel structure
• The area above the ordinal dominance graph and the area below the receiver operating characteristic graph

This page was built for publication: Step function based light Newton-like method for AUC

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6938709)