Regularization networks and support vector machines

DOI10.1023/A:1018946025316zbMATH Open0939.68098DBLPjournals/adcm/EvgeniouPP00OpenAlexW2110652811WikidataQ63508138 ScholiaQ63508138MaRDI QIDQ1968640FDOQ1968640

Authors: Theodoros Evgeniou, Massimiliano Pontil, T. Poggio 

Publication date: 21 March 2000

Published in: Advances in Computational Mathematics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1023/a:1018946025316

Recommendations

• The equivalence of support vector machine and regularization neural networks
• Regularization, optimization, kernels, and support vector machines
• Support-vector networks
• Regularization algorithms for learning that are equivalent to multilayer networks
• scientific article; zbMATH DE number 778115
• Kernel Based Learning Methods: Regularization Networks and RBF Networks
• Support vector machines regression with \(l^1\)-regularizer
• Regularization networks with indefinite kernels

zbMATH Keywords

regularizationreproducing kernel Hilbert spacesupport vector machinesradial basis functionsstructural risk minimization

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cited In (only showing first 100 items - show all)

• Kernel-based sparse regression with the correntropy-induced loss
• Approximation of Lyapunov functions from noisy data
• Multikernel regression with sparsity constraint
• The equivalence of support vector machine and regularization neural networks
• Bayesian frequentist bounds for machine learning and system identification
• Mean field method for the support vector machine regression
• Learning dynamical systems using local stability priors
• Efficient spatio-temporal Gaussian regression via Kalman filtering
• Error analysis of the kernel regularized regression based on refined convex losses and RKBSs
• Calibration of \(\epsilon\)-insensitive loss in support vector machines regression
• Full-body person recognition system.
• Mini-workshop: Deep learning and inverse problems. Abstracts from the mini-workshop held March 4--10, 2018
• Density problem and approximation error in learning theory
• Title not available (Why is that?)
• A representer theorem for deep neural networks
• SVM-boosting based on Markov resampling: theory and algorithm
• An analytic center machine for regression
• Online classification with varying Gaussians
• Generalized regularized least-squares approximation of noisy data with application to stochastic PDEs
• Fast computation of smoothing splines subject to equality constraints
• Supervised Learning by Support Vector Machines
• On the stability of reproducing kernel Hilbert spaces of discrete-time impulse responses
• An Algorithm for Unconstrained Quadratically Penalized Convex Optimization
• Influence diagnostics in support vector machines
• Approximation of high-dimensional kernel matrices by multilevel circulant matrices
• Support vector machines regression with unbounded sampling
• A general learning framework using local and global regularization
• Learning theory: from regression to classification
• Distributed regression learning with coefficient regularization
• A new method for sparsity control in support vector classification and regression
• Nonlinear system identification via data augmentation
• Regularized least square algorithm with two kernels
• On the \(K\)-functional in learning theory
• Kernel methods for the approximation of nonlinear systems
• Efficient regularized least-squares algorithms for conditional ranking on relational data
• Learning with convex loss and indefinite kernels
• A computationally efficient scheme for feature extraction with kernel discriminant analysis
• Estimating interest rate curves by support vector regression
• A variational relevance vector machine for classification and regression problems with multidimensional feature arrays
• Parsimonious online learning with kernels via sparse projections in function space
• On the inclusion relation of reproducing kernel Hilbert spaces
• Balancing principle in supervised learning for a general regularization scheme
• Distribution-free consistency of empirical risk minimization and support vector regression
• Hierarchical sparse method with applications in vision and speech recognition
• Improving the solution of least squares support vector machines with application to a blast furnace system
• On a regularization of unsupervised domain adaptation in RKHS
• Boosted kernel ridge regression: optimal learning rates and early stopping
• Dual bases and discrete reproducing kernels: a unified framework for RBF and MLS approximation
• Boosting as a kernel-based method
• A unifying representer theorem for inverse problems and machine learning
• Classifier learning with a new locality regularization method
• Kernel absolute summability is sufficient but not necessary for RKHS stability
• Investigation of the relationship between support vector machines and neural networks
• Title not available (Why is that?)
• Regularization algorithms for learning that are equivalent to multilayer networks
• Learning rates for regularized classifiers using multivariate polynomial kernels
• Similarity, kernels, and the fundamental constraints on cognition
• Spectral Algorithms for Supervised Learning
• Kernel methods in system identification, machine learning and function estimation: a survey
• Optimal learning rates for kernel partial least squares
• Gaussian processes for object categorization
• Shannon sampling and function reconstruction from point values
• Leave-One-Out Bounds for Kernel Methods
• Forecasting stock market movement direction with support vector machine
• Regularized least square regression with spherical polynomial kernels
• Optimal sampling points in reproducing kernel Hilbert spaces
• Model selection approaches for non-linear system identification: a review
• Reproducing kernel Banach spaces with the \(\ell^{1}\) norm. II: Error analysis for regularized least square regression
• Robust generalized eigenvalue classifier with ellipsoidal uncertainty
• Another look at statistical learning theory and regularization
• Tikhonov, Ivanov and Morozov regularization for support vector machine learning
• Learning rates for least square regressions with coefficient regularization
• ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY
• Discriminatively regularized least-squares classification
• Bayes and empirical Bayes semi-blind deconvolution using eigenfunctions of a prior covariance
• Analysis of support vector machines regression
• Multicategory proximal support vector machine classifiers
• Learning rates for the kernel regularized regression with a differentiable strongly convex loss
• Least square regression with \(l^{p}\)-coefficient regularization
• Convergence analysis of online algorithms
• Comment on: ``Support vector machines with applications
• Approximation with polynomial kernels and SVM classifiers
• Learning theory: stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk minimization
• Statistical properties of the method of regularization with periodic Gaussian reproducing kernel
• Tuning complexity in regularized kernel-based regression and linear system identification: the robustness of the marginal likelihood estimator
• DISCRETIZATION ERROR ANALYSIS FOR TIKHONOV REGULARIZATION
• On kernel design for regularized LTI system identification
• Learning and approximation by Gaussians on Riemannian manifolds
• On the mathematical foundations of learning
• Least square regression with indefinite kernels and coefficient regularization
• On the rate of convergence for multi-category classification based on convex losses
• The consistency of multicategory support vector machines
• Multi-penalty regularization in learning theory
• Regularization techniques and suboptimal solutions to optimization problems in learning from data
• Half supervised coefficient regularization for regression learning with unbounded sampling
• Indefinite kernel network with dependent sampling
• System identification using kernel-based regularization: new insights on stability and consistency issues
• Laplacian twin support vector machine for semi-supervised classification
• Multi-kernel regularized classifiers
• Mercer theorem for RKHS on noncompact sets

This page was built for publication: Regularization networks and support vector machines

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1968640)