Unregularized online learning algorithms with general loss functions

DOI10.1016/j.acha.2015.08.007zbMath1382.68204arXiv1503.00623OpenAlexW2964224116WikidataQ58758915 ScholiaQ58758915MaRDI QIDQ504379

Ding-Xuan Zhou, Yiming Ying

Publication date: 16 January 2017

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

Full work available at URL: https://arxiv.org/abs/1503.00623

zbMATH Keywords

learning theoryonline learningreproducing kernel Hilbert spacepairwise learningbipartite ranking

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22)

Related Items

Deep distributed convolutional neural networks: Universality, Unnamed Item, Distributed kernel gradient descent algorithm for minimum error entropy principle, Differentially private SGD with non-smooth losses, Theory of deep convolutional neural networks: downsampling, Convergence of online pairwise regression learning with quadratic loss, Convergence analysis for kernel-regularized online regression associated with an RRKHS, Federated learning for minimizing nonsmooth convex loss functions, High-probability generalization bounds for pointwise uniformly stable algorithms, Online Pairwise Learning Algorithms, Analysis of Online Composite Mirror Descent Algorithm, Online minimum error entropy algorithm with unbounded sampling, Kernel gradient descent algorithm for information theoretic learning, Generalization ability of online pairwise support vector machine, Unnamed Item, Convergence of online mirror descent, Online pairwise learning algorithms with convex loss functions, Online regularized pairwise learning with least squares loss, Fast and strong convergence of online learning algorithms, Deep neural networks for rotation-invariance approximation and learning, Analysis of regularized Nyström subsampling for regression functions of low smoothness, Analysis of singular value thresholding algorithm for matrix completion, Iterative gradient descent for outlier detection, Error analysis of the kernel regularized regression based on refined convex losses and RKBSs, Error analysis of the moving least-squares regression learning algorithm with β-mixing and non-identical sampling

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Consistency analysis of an empirical minimum error entropy algorithm
• Learning the coordinate gradients
• Model selection for regularized least-squares algorithm in learning theory
• Multi-kernel regularized classifiers
• Online gradient descent learning algorithms
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• Fully online classification by regularization
• Ranking and empirical minimization of \(U\)-statistics
• Online learning algorithms
• Online Learning as Stochastic Approximation of Regularization Paths: Optimality and Almost-Sure Convergence
• Learning Theory
• Support Vector Machines
• On the Generalization Ability of On-Line Learning Algorithms
• Online Regularized Classification Algorithms
• Some comparisons for Gaussian processes
• 10.1162/1532443041424300
• 10.1162/153244303321897690
• Regularization schemes for minimum error entropy principle
• Convexity, Classification, and Risk Bounds
• Theory of Reproducing Kernels