Kernel conjugate gradient methods with random projections

DOI10.1016/j.acha.2021.05.004OpenAlexW3164947295MaRDI QIDQ1979923

Volkan Cevher, Jun Hong Lin

Publication date: 3 September 2021

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

Full work available at URL: https://arxiv.org/abs/1811.01760

zbMATH Keywords

learning theoryintegral operatorconjugate gradient methodslearning ratesrandomized sketches

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Approximation by operators (in particular, by integral operators) (41A35) Sampling theory in information and communication theory (94A20)

Uses Software

• gss

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Kernel ridge vs. principal component regression: minimax bounds and the qualification of regularization operators
• Optimal rates for regularization of statistical inverse learning problems
• A simple proof of the restricted isometry property for random matrices
• Uniform uncertainty principle for Bernoulli and subgaussian ensembles
• Optimal learning rates for kernel partial least squares
• Randomized sketches for kernels: fast and optimal nonparametric regression
• Optimal rates for spectral algorithms with least-squares regression over Hilbert spaces
• Optimal rates for the regularized least-squares algorithm
• Learning theory estimates via integral operators and their approximations
• Convergence rates of Kernel Conjugate Gradient for random design regression
• New and Improved Johnson–Lindenstrauss Embeddings via the Restricted Isometry Property
• 10.1162/15324430260185556
• Learning Theory
• Support Vector Machines
• Decoding by Linear Programming
• CROSS-VALIDATION BASED ADAPTATION FOR REGULARIZATION OPERATORS IN LEARNING THEORY
• Remarks on Inequalities for Large Deviation Probabilities
• Norm Inequalities Equivalent to Heinz Inequality
• Faster Kernel Ridge Regression Using Sketching and Preconditioning
• Optimal Rates for Multi-pass Stochastic Gradient Methods
• Kernel partial least squares for stationary data
• Regularized Nyström subsampling in regression and ranking problems under general smoothness assumptions
• Analysis of regularized Nyström subsampling for regression functions of low smoothness
• Nyström type subsampling analyzed as a regularized projection
• An Introduction to Matrix Concentration Inequalities
• Learning Bounds for Kernel Regression Using Effective Data Dimensionality
• Methods of conjugate gradients for solving linear systems
• An operator inequality