Best choices for regularization parameters in learning theory: on the bias-variance problem.
From MaRDI portal
Publication:1865826
DOI10.1007/s102080010030zbMath1057.68085WikidataQ57733260 ScholiaQ57733260MaRDI QIDQ1865826
Publication date: 2002
Published in: Foundations of Computational Mathematics (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/s102080010030
68T05: Learning and adaptive systems in artificial intelligence
62J10: Analysis of variance and covariance (ANOVA)
Related Items
Shannon sampling and function reconstruction from point values, Are Loss Functions All the Same?, REGULARIZED LEAST SQUARE REGRESSION WITH SPHERICAL POLYNOMIAL KERNELS, LEARNING RATES OF REGULARIZED REGRESSION FOR FUNCTIONAL DATA, AN ERROR ANALYSIS OF LAVRENTIEV REGULARIZATION IN LEARNING THEORY, Rejoinder, Learning from regularized regression algorithms with \(p\)-order Markov chain sampling, Generalization bounds of ERM algorithm with \(V\)-geometrically ergodic Markov chains, Estimation of convergence rate for multi-regression learning algorithm, Mercer theorem for RKHS on noncompact sets, Learning with generalization capability by kernel methods of bounded complexity, Least square regression with indefinite kernels and coefficient regularization, Learning performance of Tikhonov regularization algorithm with geometrically beta-mixing observations, On the interplay between entropy and robustness of gene regulatory networks, Generalization performance of least-square regularized regression algorithm with Markov chain samples, Regularization in kernel learning, Multi-kernel regularized classifiers, Fourier frequencies in affine iterated function systems, Learning rates for regularized classifiers using multivariate polynomial kernels, On the mathematics of emergence, Flocking with informed agents, Analysis of support vector machines regression, Learning from uniformly ergodic Markov chains, Estimates of the norm of the Mercer kernel matrices with discrete orthogonal transforms, Positive definite dot product kernels in learning theory, The generalization performance of ERM algorithm with strongly mixing observations, The weight-decay technique in learning from data: an optimization point of view, Complexity control in statistical learning, Learning with sample dependent hypothesis spaces, Application of integral operator for regularized least-square regression, Learning rates of regularized regression for exponentially strongly mixing sequence, A consistent algorithm to solve Lasso, elastic-net and Tikhonov regularization, Flocking in noisy environments, Additive regularization trade-off: fusion of training and validation levels in kernel methods, Approximation with polynomial kernels and SVM classifiers, Shannon sampling. II: Connections to learning theory, Binary separation and training support vector machines, THE COEFFICIENT REGULARIZED REGRESSION WITH RANDOM PROJECTION, Least Square Regression with lp-Coefficient Regularization, Error analysis of multicategory support vector machine classifiers, GENERALIZATION BOUNDS OF REGULARIZATION ALGORITHMS DERIVED SIMULTANEOUSLY THROUGH HYPOTHESIS SPACE COMPLEXITY, ALGORITHMIC STABILITY AND DATA QUALITY, LOCAL LEARNING ESTIMATES BY INTEGRAL OPERATORS, DISCRETIZATION ERROR ANALYSIS FOR TIKHONOV REGULARIZATION, Applications of the Bernstein-Durrmeyer operators in estimating the norm of Mercer kernel matrices, Regularization Techniques and Suboptimal Solutions to Optimization Problems in Learning from Data
