K-plane regression

DOI10.1016/J.INS.2014.08.058MaRDI QIDQ508945zbMATH OpenOpenAlexFDO

Authors Naresh Manwani, P. S. Sastry

Publication date 8 February 2017

Published in Information Sciences (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1211.1513

zbMATH Keywords

expectation maximizationmixture of expertscluster-wise linear regressionpiecewise linear regression

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) General nonlinear regression (62J02)

Abstract: In this paper, we present a novel algorithm for piecewise linear regression which can learn continuous as well as discontinuous piecewise linear functions. The main idea is to repeatedly partition the data and learn a liner model in in each partition. While a simple algorithm incorporating this idea does not work well, an interesting modification results in a good algorithm. The proposed algorithm is similar in spirit to $k$-means clustering algorithm. We show that our algorithm can also be viewed as an EM algorithm for maximum likelihood estimation of parameters under a reasonable probability model. We empirically demonstrate the effectiveness of our approach by comparing its performance with the state of art regression learning algorithms on some real world datasets.

Recommendations

• Kernel dimension reduction in regression
• 10.1162/15324430260185556
• An affine invariant \(k\)-nearest neighbor regression estimate
• scientific article; zbMATH DE number 1551793
• Kernel ridge regression
• A note on kernel principal component regression
• k-Vectors: An Alternating Minimization Algorithm for Learning Regression Functions
• Kernel spline regression
• Gradient-based kernel dimension reduction for regression
• Kernel estimators for multivariate regression

Cites work

• scientific article; zbMATH DE number 3860199 (Why is no real title available?)
• scientific article; zbMATH DE number 51537 (Why is no real title available?)
• scientific article; zbMATH DE number 1956624 (Why is no real title available?)
• A bounded-error approach to piecewise affine system identification
• A class of fuzzy clusterwise regression models
• A fast algorithm for clusterwise linear regression
• A hybrid-forecasting model reducing Gaussian noise based on the Gaussian support vector regression machine and chaotic particle swarm optimization
• A maximum likelihood methodology for clusterwise linear regression
• Estimation of a Regression Function by Maxima of Minima of Linear Functions
• Hinging hyperplanes for regression, classification, and function approximation
• Identification of hybrid systems. A tutorial
• Nonlinear Programming
• Nonsmooth nonconvex optimization approach to clusterwise linear regression problems
• On the hinge-finding algorithm for hingeing hyperplanes
• Online independent reduced least squares support vector regression
• PRMLT
• Pattern recognition and machine learning.
• The MIN PFS problem and piecewise linear model estimation
• The elements of statistical learning. Data mining, inference, and prediction

Cited in

(4)

• Scalable and near-optimal \(\varepsilon\)-tube clusterwise regression
• Performance characterization of clusterwise linear regression algorithms
• An EM-based ensemble learning algorithm on piecewise surface regression problem
• scientific article; zbMATH DE number 1928654 (Why is no real title available?)

Describes a project that uses

Uses Software

• PRMLT
• Algorithm 39
• LIBSVM
• UCI

This page was built for publication: \(K\)-plane regression

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q508945)