Regularized learning schemes in feature Banach spaces

DOI10.1142/S0219530516500202zbMath1378.62015arXiv1410.6847OpenAlexW2963099468WikidataQ47037073 ScholiaQ47037073MaRDI QIDQ4594821

Patrick L. Combettes, Saverio Salzo, Silvia Villa

Publication date: 24 November 2017

Published in: Analysis and Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1410.6847

zbMATH Keywords

Banach spacesconsistencyregularizationreproducing kernelstatistical learningtotally convex functionempirical riskrepresenter theoremfeature map

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Learning and adaptive systems in artificial intelligence (68T05) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Applications of functional analysis in probability theory and statistics (46N30) Probability theory on linear topological spaces (60B11)

Related Items

Explicit representations for Banach subspaces of Lizorkin distributions ⋮ Sparse machine learning in Banach spaces ⋮ Thresholding gradient methods in Hilbert spaces: support identification and linear convergence ⋮ Optimal Algorithms for Stochastic Complementary Composite Minimization ⋮ Bias reduction in variational regularization ⋮ Sufficient ensemble size for random matrix theory-based handling of singular covariance matrices ⋮ A unifying representer theorem for inverse problems and machine learning ⋮ Consistent learning by composite proximal thresholding ⋮ The global convergence of the nonlinear power method for mixed-subordinate matrix norms ⋮ Generalized support vector regression: Duality and tensor-kernel representation ⋮ Concentration of weakly dependent Banach-valued sums and applications to statistical learning methods ⋮ Understanding neural networks with reproducing kernel Banach spaces ⋮ Error analysis of the kernel regularized regression based on refined convex losses and RKBSs ⋮ An efficient collocation algorithm with SSP-RK43 scheme to solve Rosenau-KdV-RLW equation

Uses Software

• fda (R)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Fast learning rate of multiple kernel learning: trade-off between sparsity and smoothness
• Two oracle inequalities for regularized boosting classifiers
• Solving support vector machines in reproducing kernel Banach spaces with positive definite functions
• Statistics for high-dimensional data. Methods, theory and applications.
• Optimal learning rates for least squares regularized regression with unbounded sampling
• Convex functions, monotone operators and differentiability.
• Regularized learning in Banach spaces as an optimization problem: representer theorems
• Convexity and well-posed problems
• Sparsity in penalized empirical risk minimization
• Kernel methods in machine learning
• Elastic-net regularization in learning theory
• On uniformly convex functionals
• Characteristic inequalities of uniformly convex and uniformly smooth Banach spaces
• Convex analysis and measurable multifunctions
• Iterative averaging of entropic projections for solving stochastic convex feasibility problems
• Totally convex functions for fixed points computation and infinite dimensional optimization
• Reproducing kernel Banach spaces with the \(\ell^1\) norm
• A distribution-free theory of nonparametric regression
• Sums and Gaussian vectors
• Weak convergence and empirical processes. With applications to statistics
• Vector-valued reproducing kernel Banach spaces with applications to multi-task learning
• Kernel regression with functional response
• Functional data analysis.
• Bregman distances, totally convex functions, and a method for solving operator equations in Banach spaces
• Continuity properties of projection operators
• Learning rates of least-square regularized regression
• Integral representation of dominated operations on spaces of continuous vector fields
• Local Rademacher complexities
• On the mathematical foundations of learning
• Accelerated and Inexact Forward-Backward Algorithms
• Spaces of Operator-valued Functions Measurable with Respect to the Strong Operator Topology
• Variational Analysis in Sobolev and BV Spaces
• Reproducing Kernel Banach Spaces with the ℓ¹ Norm II: Error Analysis for Regularized Least Square Regression
• VECTOR VALUED REPRODUCING KERNEL HILBERT SPACES AND UNIVERSALITY
• VECTOR VALUED REPRODUCING KERNEL HILBERT SPACES OF INTEGRABLE FUNCTIONS AND MERCER THEOREM
• Learning Theory
• Support Vector Machines
• Proximal Thresholding Algorithm for Minimization over Orthonormal Bases
• Inequalities in Banach spaces with applications
• Quantitative Stability of Variational Systems: I. The Epigraphical Distance
• Wavelet thresholding for some classes of non–Gaussian noise
• A family of minimax rates for density estimators in continuous time
• Learning Theory
• 10.1162/153244303321897690
• Viscosity Solutions of Minimization Problems
• Strong Convergence of Block-Iterative Outer Approximation Methods for Convex Optimization
• Regularization and Variable Selection Via the Elastic Net
• A Correspondence Between Bayesian Estimation on Stochastic Processes and Smoothing by Splines
• On Learning Vector-Valued Functions
• Convex analysis and monotone operator theory in Hilbert spaces
• Introduction to nonparametric estimation
• On uniformly convex functions