Loss Functions for Finite Sets

DOI10.1007/S10589-022-00420-9MaRDI QIDQ6385373arXivFDO

Authors Jiawang Nie, Suhan Zhong

Publication date 11 December 2021

Published in arXiv

Full work available at URL https://doi.org/10.1007/S10589-022-00420-9

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Polynomial optimization (90C23) Nonlinear programming (90C30)

arXiv classification

math.OC

Abstract: This paper studies loss functions for finite sets. For a given finite set $S$, we give sum-of-square type loss functions of minimum degree. When $S$ is the vertex set of a standard simplex, we show such loss functions have no spurious minimizers (i.e., every local minimizer is a global one). Up to transformations, we give similar loss functions without spurious minimizers for general finite sets. When $S$ is approximately given by a sample set $T$, we show how to get loss functions by solving a quadratic optimization problem. Numerical experiments and applications are given to show the efficiency of these loss functions.

This page was built for publication: Loss Functions for Finite Sets

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6385373)