Distributed kernel-based gradient descent algorithms

DOI10.1007/s00365-017-9379-1zbMath1390.68542OpenAlexW2615421548MaRDI QIDQ1745365

Ding-Xuan Zhou, Shao-Bo Lin

Publication date: 17 April 2018

Published in: Constructive Approximation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s00365-017-9379-1

zbMATH Keywords

learning theoryintegral operatordistributed learninggradient descent algorithm

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Approximation by operators (in particular, by integral operators) (41A35)

Related Items (26)

A review of distributed statistical inference ⋮ Nonparametric regression using needlet kernels for spherical data ⋮ Toward Efficient Ensemble Learning with Structure Constraints: Convergent Algorithms and Applications ⋮ Distributed learning via filtered hyperinterpolation on manifolds ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Distributed kernel gradient descent algorithm for minimum error entropy principle ⋮ Distributed semi-supervised regression learning with coefficient regularization ⋮ Theory of deep convolutional neural networks: downsampling ⋮ Theory of deep convolutional neural networks. III: Approximating radial functions ⋮ Approximating smooth and sparse functions by deep neural networks: optimal approximation rates and saturation ⋮ Fully corrective gradient boosting with squared hinge: fast learning rates and early stopping ⋮ Neural network interpolation operators optimized by Lagrange polynomial ⋮ Learning sparse and smooth functions by deep sigmoid nets ⋮ Decentralized learning over a network with Nyström approximation using SGD ⋮ Communication-efficient estimation of high-dimensional quantile regression ⋮ Kernel regression, minimax rates and effective dimensionality: Beyond the regular case ⋮ Unnamed Item ⋮ Distributed regularized least squares with flexible Gaussian kernels ⋮ Theory of deep convolutional neural networks. II: Spherical analysis ⋮ Deep neural networks for rotation-invariance approximation and learning ⋮ Semi-supervised learning with summary statistics ⋮ Distributed Filtered Hyperinterpolation for Noisy Data on the Sphere ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Distributed least squares prediction for functional linear regression*

Uses Software

• MapReduce

Cites Work

• Kernel ridge vs. principal component regression: minimax bounds and the qualification of regularization operators
• On regularization algorithms in learning theory
• Weak convergence and empirical processes. With applications to statistics
• Optimal rates for the regularized least-squares algorithm
• Learning with sample dependent hypothesis spaces
• 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
• Spectral Algorithms for Supervised Learning
• Capacity of reproducing kernel spaces in learning theory
• CROSS-VALIDATION BASED ADAPTATION FOR REGULARIZATION OPERATORS IN LEARNING THEORY
• Real Analysis and Probability
• Regularization schemes for minimum error entropy principle
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Distributed kernel-based gradient descent algorithms