Polynomial expansion of the binary classification function

2012/03/26 by Péter Kövesárki, Kövesárki, Péter
Mathematics · #62J02 #FOS: Computer and information sciences #Machine Learning (stat.ML) #msc:62J02 #stat.ML

paper · pdf · doi:10.48550/arxiv.1203.5647

6 pages, 6 figures. Submitted to JMLR, pending decision

arxiv created 2012/03/26 · arxiv updated 2012/03/27

Abstract

This paper describes a novel method to approximate the polynomial coefficients of regression functions, with particular interest on multi-dimensional classification. The derivation is simple, and offers a fast, robust classification technique that is resistant to over-fitting.

Related

• Learning the Kernel for Classification and Regression
• Multivariate Polynomial Regression of Euclidean Degree Extends the Stability for Fast Approximations of Trefethen Functions
• Bagged Polynomial Regression and Neural Networks
• Local Polynomial Regression Based on Functional Data
• Stretchy Polynomial Regression