Learning theory of distributed spectral algorithms

DOI10.1088/1361-6420/AA72B2zbMath1372.65162OpenAlexW2613940844MaRDI QIDQ5348011

Ding-Xuan Zhou, Zheng-Chu Guo, Shao-Bo Lin

Publication date: 11 August 2017

Published in: Inverse Problems (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1088/1361-6420/aa72b2

zbMATH Keywords

inverse operatorerror boundreproducing kernel Hilbert spacespectral algorithmdistributed learninglearning ratedivide-and-conquer approach

Mathematics Subject Classification ID

Linear regression; mixed models (62J05) Learning and adaptive systems in artificial intelligence (68T05) Integral operators (47G10) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Numerical solution to inverse problems in abstract spaces (65J22)

Related Items (52)

Distributed spectral pairwise ranking algorithms ⋮ Distributed regression learning with coefficient regularization ⋮ Deep distributed convolutional neural networks: Universality ⋮ Distributed learning via filtered hyperinterpolation on manifolds ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Gradient descent for robust kernel-based regression ⋮ Distributed learning with partial coefficients regularization ⋮ Manifold regularization based on Nyström type subsampling ⋮ Distributed kernel gradient descent algorithm for minimum error entropy principle ⋮ Multi-task learning via linear functional strategy ⋮ Distributed semi-supervised regression learning with coefficient regularization ⋮ Averaging versus voting: a comparative study of strategies for distributed classification ⋮ Distributed learning with multi-penalty regularization ⋮ Preface for Inverse Problems special issue on learning and inverse problems ⋮ Spectral algorithms for learning with dependent observations ⋮ Capacity dependent analysis for functional online learning algorithms ⋮ Distributed learning for sketched kernel regression ⋮ Tikhonov regularization with oversmoothing penalty for nonlinear statistical inverse problems ⋮ Convex regularization in statistical inverse learning problems ⋮ Domain Generalization by Functional Regression ⋮ Inverse learning in Hilbert scales ⋮ Estimates on learning rates for multi-penalty distribution regression ⋮ Coefficient-based regularized distribution regression ⋮ Online regularized learning algorithm for functional data ⋮ Communication-efficient estimation of high-dimensional quantile regression ⋮ Distributed learning and distribution regression of coefficient regularization ⋮ Kernel regression, minimax rates and effective dimensionality: Beyond the regular case ⋮ On the Improved Rates of Convergence for Matérn-Type Kernel Ridge Regression with Application to Calibration of Computer Models ⋮ Coefficient-based regularization network with variance loss for error ⋮ Robust kernel-based distribution regression ⋮ Unnamed Item ⋮ Partially functional linear regression with quadratic regularization ⋮ Distributed SGD in overparametrized linear regression ⋮ Learning with centered reproducing kernels ⋮ Balancing principle in supervised learning for a general regularization scheme ⋮ Convergence of online mirror descent ⋮ Optimal learning rates for distribution regression ⋮ Distributed estimation of principal eigenspaces ⋮ Analysis of regularized least squares for functional linear regression model ⋮ Universality of deep convolutional neural networks ⋮ Optimal rates for spectral algorithms with least-squares regression over Hilbert spaces ⋮ Regularized Nyström subsampling in regression and ranking problems under general smoothness assumptions ⋮ Semi-supervised learning with summary statistics ⋮ Distributed learning with indefinite kernels ⋮ Unnamed Item ⋮ Optimal rates for coefficient-based regularized regression ⋮ Distributed Filtered Hyperinterpolation for Noisy Data on the Sphere ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Distributed least squares prediction for functional linear regression*

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Random design analysis of ridge regression
• On regularization algorithms in learning theory
• The covering number in learning theory
• Optimal rates for the regularized least-squares algorithm
• Shannon sampling. II: Connections to learning theory
• Learning theory estimates via integral operators and their approximations
• On early stopping in gradient descent learning
• Divide and Conquer Kernel Ridge Regression: A Distributed Algorithm with Minimax Optimal Rates
• Learning Theory
• Spectral Algorithms for Supervised Learning
• CROSS-VALIDATION BASED ADAPTATION FOR REGULARIZATION OPERATORS IN LEARNING THEORY
• Generalization performance of regularization networks and support vector machines via entropy numbers of compact operators
• Shannon sampling and function reconstruction from point values
• Regularization schemes for minimum error entropy principle

This page was built for publication: Learning theory of distributed spectral algorithms