Optimal rates for spectral algorithms with least-squares regression over Hilbert spaces

DOI10.1016/j.acha.2018.09.009zbMath1436.62146arXiv1801.06720MaRDI QIDQ2300763

Lorenzo Rosasco, Alessandro Rudi, Volkan Cevher, Jun Hong Lin

Publication date: 28 February 2020

Published in: Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1801.06720

zbMATH Keywords

learning theory; ridge regression; regression; reproducing kernel Hilbert space; principal component regression; regularization scheme; sampling operator

Mathematics Subject Classification ID

62G08: Nonparametric regression and quantile regression

62H25: Factor analysis and principal components; correspondence analysis

62J07: Ridge regression; shrinkage estimators (Lasso)

62M15: Inference from stochastic processes and spectral analysis

68T05: Learning and adaptive systems in artificial intelligence

46E22: Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces)

Related Items

Unnamed Item, Unnamed Item, Unnamed Item, Unnamed Item, Error analysis of the kernel regularized regression based on refined convex losses and RKBSs, Regularization: From Inverse Problems to Large-Scale Machine Learning, Generalization error rates in kernel regression: the crossover from the noiseless to noisy regime*, Analysis of regularized Nyström subsampling for regression functions of low smoothness, Spectral algorithms for learning with dependent observations, Mini-workshop: Mathematical foundations of robust and generalizable learning. Abstracts from the mini-workshop held October 2--8, 2022, Inverse learning in Hilbert scales, Kernel conjugate gradient methods with random projections, Distributed regularized least squares with flexible Gaussian kernels, Sparse high-dimensional semi-nonparametric quantile regression in a reproducing kernel Hilbert space, From inexact optimization to learning via gradient concentration, Machine learning with kernels for portfolio valuation and risk management, Learning rates for the kernel regularized regression with a differentiable strongly convex loss, Convergence analysis of Tikhonov regularization for non-linear statistical inverse problems, Kernel gradient descent algorithm for information theoretic learning, Kernel regression, minimax rates and effective dimensionality: Beyond the regular case

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Random design analysis of ridge regression
• Kernel ridge vs. principal component regression: minimax bounds and the qualification of regularization operators
• On regularization algorithms in learning theory
• Double operator integrals in a Hilbert space
• Optimal rates for the regularized least-squares algorithm
• Learning rates of least-square regularized regression
• Boosting with early stopping: convergence and consistency
• Learning theory estimates via integral operators and their approximations
• On early stopping in gradient descent learning
• Regularization of some linear ill-posed problems with discretized random noisy data
• Learning Theory
• Support Vector Machines
• Spectral Algorithms for Supervised Learning
• Remarks on Inequalities for Large Deviation Probabilities
• Norm Inequalities Equivalent to Heinz Inequality
• Optimal Rates for Multi-pass Stochastic Gradient Methods
• MODULI OF CONTINUITY FOR OPERATOR VALUED FUNCTIONS
• Regularized Nyström subsampling in regression and ranking problems under general smoothness assumptions
• Learning theory of distributed spectral algorithms
• Learning Bounds for Kernel Regression Using Effective Data Dimensionality