Distributed kernel gradient descent algorithm for minimum error entropy principle

DOI10.1016/j.acha.2019.01.002zbMath1434.68416WikidataQ128593977 ScholiaQ128593977MaRDI QIDQ2175022

Qiang Wu, Ting Hu, Ding-Xuan Zhou

Publication date: 27 April 2020

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

Full work available at URL: https://doi.org/10.1016/j.acha.2019.01.002

zbMATH Keywords

kernel method; minimum error entropy; distributed learning; gradient descent algorithm

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

94A17: Measures of information, entropy

68T09: Computational aspects of data analysis and big data

Related Items

Unnamed Item, Unnamed Item, A Framework of Learning Through Empirical Gain Maximization, Unnamed Item, Learning theory of minimum error entropy under weak moment conditions, Distributed spectral pairwise ranking algorithms, Robust kernel-based distribution regression, Convergence analysis of distributed multi-penalty regularized pairwise learning, Block coordinate type methods for optimization and learning, Infinite-dimensional stochastic transforms and reproducing kernel Hilbert space, Distributed regularized least squares with flexible Gaussian kernels, Fast rates of minimum error entropy with heavy-tailed noise, Kernel-based maximum correntropy criterion with gradient descent method, Kernel gradient descent algorithm for information theoretic learning, Averaging versus voting: a comparative study of strategies for distributed classification

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Consistency analysis of an empirical minimum error entropy algorithm
• Unregularized online learning algorithms with general loss functions
• Stochastic gradient algorithm under \((h, \phi)\)-entropy criterion
• Distributed kernel-based gradient descent algorithms
• Blind source separation using Renyi's \(\alpha\)-marginal entropies.
• Optimum bounds for the distributions of martingales in Banach spaces
• Deep relaxation: partial differential equations for optimizing deep neural networks
• Optimal rates for the regularized least-squares algorithm
• On early stopping in gradient descent learning
• Divide and Conquer Kernel Ridge Regression: A Distributed Algorithm with Minimax Optimal Rates
• The MEE Principle in Data Classification: A Perceptron-Based Analysis
• Learning Theory
• Minimum Total Error Entropy Method for Parameter Estimation
• On the optimality of averaging in distributed statistical learning
• Convergence of Gradient Descent for Minimum Error Entropy Principle in Linear Regression
• Regularization schemes for minimum error entropy principle
• Thresholded spectral algorithms for sparse approximations
• Learning theory of distributed spectral algorithms
• Online Pairwise Learning Algorithms