Convergence of unregularized online learning algorithms

MaRDI QIDQ4558495zbMATH OpenFDO

Authors Yunwen Lei, Lei Shi, Zheng-Chu Guo

Publication date 22 November 2018

Full work available at URL https://arxiv.org/abs/1708.02939, http://jmlr.csail.mit.edu/papers/v18/17-457.html

zbMATH Keywords

learning theoryreproducing kernel Hilbert spaceconvergence analysisonline learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Online algorithms; streaming algorithms (68W27) Strong limit theorems (60F15) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Martingales with continuous parameter (60G44) (L^p)-limit theorems (60F25)

Recommendations

• Unregularized online learning algorithms with general loss functions
• Fast and strong convergence of online learning algorithms
• Convergence analysis of online algorithms
• Online gradient descent learning algorithms
• Online learning algorithms

Cites work

• scientific article; zbMATH DE number 515978 (Why is no real title available?)
• scientific article; zbMATH DE number 1569102 (Why is no real title available?)
• Efficient online and batch learning using forward backward splitting
• Fully online classification by regularization
• Information-Theoretic Lower Bounds on the Oracle Complexity of Stochastic Convex Optimization
• Learning Theory
• Learning Theory
• Learning theory of randomized Kaczmarz algorithm
• Nonparametric stochastic approximation with large step-sizes
• ONLINE LEARNING WITH MARKOV SAMPLING
• On Complexity Issues of Online Learning Algorithms
• On the Generalization Ability of On-Line Learning Algorithms
• On the influence of the kernel on the consistency of support vector machines
• Online Learning as Stochastic Approximation of Regularization Paths: Optimality and Almost-Sure Convergence
• Online Learning with Kernels
• Online Regularized Classification Algorithms
• Online gradient descent learning algorithms
• Online learning algorithms
• Pegasos: primal estimated sub-gradient solver for SVM
• Probability Inequalities for Sums of Bounded Random Variables
• Robust Stochastic Approximation Approach to Stochastic Programming
• Support Vector Machines
• Support vector machine soft margin classifiers: error analysis
• Support-vector networks
• Unregularized online learning algorithms with general loss functions

Cited in

(11)

• Convergence of online mirror descent
• Fast and strong convergence of online learning algorithms
• Convergence analysis of online algorithms
• Online sufficient dimension reduction through sliced inverse regression
• Unregularized online algorithms with varying Gaussians
• Online gradient descent learning algorithms
• Convergence analysis for kernel-regularized online regression associated with an RRKHS
• Convergence analysis of online learning algorithm with two-stage step size
• Unregularized online learning algorithms with general loss functions
• Sparse online regression algorithm with insensitive loss functions
• Differentially private SGD with random features

Describes a project that uses

Uses Software

• Pegasos

This page was built for publication: Convergence of unregularized online learning algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4558495)