Nondegenerate Piecewise Linear Systems: A Finite Newton Algorithm and Applications in Machine Learning

DOI10.1162/NECO_a_00241zbMath1256.65062WikidataQ44804457 ScholiaQ44804457MaRDI QIDQ2919402

Shuicheng Yan, Xiaotong Yuan

Publication date: 2 October 2012

Published in: Neural Computation (Search for Journal in Brave)

zbMATH Keywords

convergencenumerical resultslinear complementarity problempiecewise linear systemsmachine learningdamped Newton methodnondegenerate coefficient matrix

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Learning and adaptive systems in artificial intelligence (68T05) Quadratic programming (90C20) Methods of quasi-Newton type (90C53) Iterative numerical methods for linear systems (65F10)

Related Items (3)

Direct solution of piecewise linear systems ⋮ Convergence results for some piecewise linear solvers ⋮ Unnamed Item

Cites Work

• Unnamed Item
• On a semi-smooth Newton method and its globalization
• Semi-implicit finite difference methods for the two-dimensional shallow water equations
• A Newton-type method for positive-semidefinite linear complementarity problems
• Newton's method for the nonlinear complementarity problem: a B- differentiable equation approach
• Newton's Method for B-Differentiable Equations
• Iterative Solution of Piecewise Linear Systems and Applications to Flows in Porous Media
• Iterative Solution of Piecewise Linear Systems
• Sparse matrix test problems
• A staggered conservative scheme for every Froude number in rapidly varied shallow water flows
• Convergence Analysis of Some Algorithms for Solving Nonsmooth Equations
• A Reflective Newton Method for Minimizing a Quadratic Function Subject to Bounds on Some of the Variables
• De-noising by soft-thresholding
• Training a Support Vector Machine in the Primal
• Model Selection and Estimation in Regression with Grouped Variables
• A Correspondence Between Bayesian Estimation on Stochastic Processes and Smoothing by Splines
• The Linear Complementarity Problem
• Corrector‐Predictor Methods for Sufficient Linear Complementarity Problems in a Wide Neighborhood of the Central Path
• Numerical Solution of Obstacle and Parabolic Obstacle Problems based on Piecewise Linear Systems
• On Newton-type approach for piecewise linear systems

This page was built for publication: Nondegenerate Piecewise Linear Systems: A Finite Newton Algorithm and Applications in Machine Learning