Intrinsic Dimension Adaptive Partitioning for Kernel Methods

DOI10.1137/21M1435690zbMath1491.68154arXiv2107.07750OpenAlexW3185132568MaRDI QIDQ5089718

Ingo Steinwart, Thomas Hamm

Publication date: 15 July 2022

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2107.07750

zbMATH Keywords

classificationcurse of dimensionalityregressionlearning rates

Mathematics Subject Classification ID

Ridge regression; shrinkage estimators (Lasso) (62J07) Learning and adaptive systems in artificial intelligence (68T05) Computational aspects of data analysis and big data (68T09)

Related Items

The effect of intrinsic dimension on the Bayes-error of projected quadratic discriminant classification

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Bayesian manifold regression
• A tree-based regressor that adapts to intrinsic dimension
• Outer Minkowski content for some classes of closed sets
• Learning and approximation by Gaussians on Riemannian manifolds
• Fast rates for support vector machines using Gaussian kernels
• Fast learning rates for plug-in classifiers
• Smooth discrimination analysis
• Lectures on analysis on metric spaces
• Improved classification rates under refined margin conditions
• Optimal global rates of convergence for nonparametric regression
• Optimal aggregation of classifiers in statistical learning.
• Optimal regression rates for SVMs using Gaussian kernels
• Adaptive learning rates for support vector machines working on data with low intrinsic dimension
• On deep learning as a remedy for the curse of dimensionality in nonparametric regression
• A note on the dimensions of Assouad and Aikawa
• Divide and Conquer Kernel Ridge Regression: A Distributed Algorithm with Minimax Optimal Rates
• SVM LEARNING AND L^p APPROXIMATION BY GAUSSIANS ON RIEMANNIAN MANIFOLDS
• Support Vector Machines
• Minimax-optimal classification with dyadic decision trees
• Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
• Rates of convergence of nearest neighbor estimation under arbitrary sampling
• Adaptive nonparametric regression with the K-nearest neighbour fused lasso