Derivative-free optimization and neural networks for robust regression

DOI10.1080/02331934.2012.674946zbMath1260.90130arXiv1110.0169OpenAlexW3101253047MaRDI QIDQ3145056

John Yearwood, Gleb Beliakov, Andrei V. Kelarev

Publication date: 13 December 2012

Published in: Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1110.0169

zbMATH Keywords

global optimizationneural networksrobust regressionnon-smooth optimizationleast-trimmed squares

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Approximation methods and heuristics in mathematical programming (90C59)

Related Items (3)

Minimizing robust estimates of sums of parameterized functions ⋮ On Robust Training of Regression Neural Networks ⋮ Parallel bucket sorting on graphics processing units based on convex optimization

Uses Software

• Thrust
• GPU Quicksort

Cites Work

• Computing of high breakdown regression estimators without sorting on graphics processing units
• Fast parallel GPU-sorting using a hybrid algorithm
• To be fair or efficient or a bit of both
• RelaxMCD: smooth optimisation for the minimum covariance determinant estimator
• Maximum trimmed likelihood estimators: a unified approach, examples, and algorithms
• Multilayer feedforward networks are universal approximators
• A class of robust and fully efficient regression estimators
• Empirical evaluation of the improved rprop learning algorithms
• Outlier detection and least trimmed squares approximation using semi-definite programming
• An evolutionary algorithm for robust regression
• A Method for Minimization of Quasidifferentiable Functions
• Global non-smooth optimization in robust multivariate regression
• Benchmarking Derivative-Free Optimization Algorithms
• Multivariate Outlier Detection With High-Breakdown Estimators
• Implementation of novel methods of global and nonsmooth optimization: GANSO programming library
• Robust Statistics
• A General Qualitative Definition of Robustness
• A Simplex Method for Function Minimization
• The study of drug–reaction relationships using global optimization techniques

This page was built for publication: Derivative-free optimization and neural networks for robust regression