Proximal Operator and Optimality Conditions for Ramp Loss SVM

DOI10.1007/S11590-021-01756-7MaRDI QIDQ6354004arXivFDO

Authors Huajun Wang, Yuan-Hai Shao, Naihua Xiu

Publication date 17 November 2020

Full work available at URL https://doi.org/10.1007/S11590-021-01756-7

Nonconvex programming, global optimization (90C26) Optimality conditions and duality in mathematical programming (90C46)

arXiv classification

math.OC

Abstract: Support vector machines with ramp loss (dubbed as

L_{r}

-SVM) have attracted wide attention due to the boundedness of ramp loss. However, the corresponding optimization problem is non-convex and the given Karush-Kuhn-Tucker (KKT) conditions are only the necessary conditions. To enrich the optimality theory of

L_{r}

-SVM and go deep into its statistical nature, we first introduce and analyze the proximal operator for ramp loss, and then establish a stronger optimality conditions: P-stationarity, which is proved to be the first-order necessary and sufficient conditions for local minimizer of

L_{r}

-SVM. Finally, we define the

L_{r}

support vectors based on the concept of P-stationary point, and show that all

L_{r}

support vectors fall into the support hyperplanes, which possesses the same feature as the one of hard margin SVM.

This page was built for publication: Proximal Operator and Optimality Conditions for Ramp Loss SVM

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6354004)