On regularization algorithms in learning theory

DOI10.1016/J.JCO.2006.07.001zbMath1109.68088OpenAlexW2123845705MaRDI QIDQ870339

Frank Bauer, Sergei V. Pereverzyev, Lorenzo Rosasco

Publication date: 12 March 2007

Published in: Journal of Complexity (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jco.2006.07.001

zbMATH Keywords

learning theoryregularization theorynon-parametric statistics

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (90)

Machine learning with kernels for portfolio valuation and risk management ⋮ Online gradient descent algorithms for functional data learning ⋮ On principal components regression, random projections, and column subsampling ⋮ Coefficient regularized regression with non-iid sampling ⋮ LOCAL LEARNING ESTIMATES BY INTEGRAL OPERATORS ⋮ Multi-penalty regularization in learning theory ⋮ Distributed spectral pairwise ranking algorithms ⋮ Optimal learning rates for kernel partial least squares ⋮ Quantum machine learning: a classical perspective ⋮ New horizons in statistical decision theory. Abstracts from the workshop held September 7--13, 2014. ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Fast rates of minimum error entropy with heavy-tailed noise ⋮ Gradient descent for robust kernel-based regression ⋮ A linear functional strategy for regularized ranking ⋮ Regularized least square regression with unbounded and dependent sampling ⋮ Sharp learning rates of coefficient-based \(l^q\)-regularized regression with indefinite kernels ⋮ Manifold regularization based on Nyström type subsampling ⋮ Multi-task learning via linear functional strategy ⋮ Distributed learning with multi-penalty regularization ⋮ Nyström type subsampling analyzed as a regularized projection ⋮ Learning theory of distributed spectral algorithms ⋮ Least square regression with indefinite kernels and coefficient regularization ⋮ Spectral algorithms for learning with dependent observations ⋮ Capacity dependent analysis for functional online learning algorithms ⋮ Learning rates for the kernel regularized regression with a differentiable strongly convex loss ⋮ Convergence analysis of Tikhonov regularization for non-linear statistical inverse problems ⋮ On the K-functional in learning theory ⋮ Convex regularization in statistical inverse learning problems ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Optimality of regularized least squares ranking with imperfect kernels ⋮ Inverse learning in Hilbert scales ⋮ A meta-learning approach to the regularized learning -- case study: blood glucose prediction ⋮ Efficient kernel canonical correlation analysis using Nyström approximation ⋮ Spectral Algorithms for Supervised Learning ⋮ Deep learning theory of distribution regression with CNNs ⋮ Coefficient-based regularized distribution regression ⋮ Online regularized learning algorithm for functional data ⋮ A neural network algorithm to pattern recognition in inverse problems ⋮ Consistency analysis of spectral regularization algorithms ⋮ Multi-output learning via spectral filtering ⋮ Bias corrected regularization kernel method in ranking ⋮ Adaptive kernel methods using the balancing principle ⋮ Convergence analysis of an empirical eigenfunction-based ranking algorithm with truncated sparsity ⋮ Kernel gradient descent algorithm for information theoretic learning ⋮ Convergence rate of kernel canonical correlation analysis ⋮ Kernel regression, minimax rates and effective dimensionality: Beyond the regular case ⋮ Optimal rates for regularization of statistical inverse learning problems ⋮ Learning rates for kernel-based expectile regression ⋮ CROSS-VALIDATION BASED ADAPTATION FOR REGULARIZATION OPERATORS IN LEARNING THEORY ⋮ Distributed kernel-based gradient descent algorithms ⋮ A Comparative Study of Pairwise Learning Methods Based on Kernel Ridge Regression ⋮ Robust kernel-based distribution regression ⋮ REGULARIZED LEAST SQUARE ALGORITHM WITH TWO KERNELS ⋮ Learning sets with separating kernels ⋮ On empirical eigenfunction-based ranking with \(\ell^1\) norm regularization ⋮ Multi-parameter regularization and its numerical realization ⋮ Sobolev error estimates and a priori parameter selection for semi-discrete Tikhonov regularization ⋮ Unnamed Item ⋮ Balancing principle in supervised learning for a general regularization scheme ⋮ Optimal learning rates for distribution regression ⋮ On the convergence rate and some applications of regularized ranking algorithms ⋮ The \(\mathrm{r}\)-\(\mathrm{d}\) class predictions in linear mixed models ⋮ Nyström subsampling method for coefficient-based regularized regression ⋮ Optimal rates for spectral algorithms with least-squares regression over Hilbert spaces ⋮ Regularized Nyström subsampling in regression and ranking problems under general smoothness assumptions ⋮ A statistical learning assessment of Huber regression ⋮ Convergence Rates of Spectral Regularization Methods: A Comparison between Ill-Posed Inverse Problems and Statistical Kernel Learning ⋮ Gradient-Based Kernel Dimension Reduction for Regression ⋮ Elastic-net regularization in learning theory ⋮ A NOTE ON STABILITY OF ERROR BOUNDS IN STATISTICAL LEARNING THEORY ⋮ Semi-supervised learning with summary statistics ⋮ Distributed learning with indefinite kernels ⋮ Optimal Rates for Multi-pass Stochastic Gradient Methods ⋮ On a regularization of unsupervised domain adaptation in RKHS ⋮ Concentration of weakly dependent Banach-valued sums and applications to statistical learning methods ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Optimal rates for coefficient-based regularized regression ⋮ Thresholding projection estimators in functional linear models ⋮ Half supervised coefficient regularization for regression learning with unbounded sampling ⋮ Analysis of singular value thresholding algorithm for matrix completion ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Error analysis of the kernel regularized regression based on refined convex losses and RKBSs ⋮ Thresholded spectral algorithms for sparse approximations ⋮ From inexact optimization to learning via gradient concentration

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Double operator integrals in a Hilbert space
• Optimal aggregation of classifiers in statistical learning.
• Weak convergence and empirical processes. With applications to statistics
• Regularization networks and support vector machines
• Optimal rates for the regularized least-squares algorithm
• Approximation methods for supervised learning
• Shannon sampling. II: Connections to learning theory
• Sous-espaces d'espaces vectoriels topologiques et noyaux associés. (Noyaux reproduisants.)
• On early stopping in gradient descent learning
• On the mathematical foundations of learning
• Theory of Classification: a Survey of Some Recent Advances
• DISCRETIZATION ERROR ANALYSIS FOR TIKHONOV REGULARIZATION
• Remarks on Inequalities for Large Deviation Probabilities
• Geometry of linear ill-posed problems in variable Hilbert scales
• MODULI OF CONTINUITY FOR OPERATOR VALUED FUNCTIONS
• Convergence Rates of General Regularization Methods for Statistical Inverse Problems and Applications
• Advanced Lectures on Machine Learning
• Convexity, Classification, and Risk Bounds
• Theory of Reproducing Kernels

This page was built for publication: On regularization algorithms in learning theory