Generalization bounds of ERM algorithm with V-geometrically ergodic Markov chains

DOI10.1007/S10444-011-9182-7zbMATH Open1242.68265OpenAlexW2084028092MaRDI QIDQ429786FDOQ429786

Xiangyu Chang, Zongben Xu, Bin Zou

Publication date: 20 June 2012

Published in: Advances in Computational Mathematics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10444-011-9182-7

Recommendations

• Generalization bounds of ERM algorithm with Markov chain samples
• Learning from uniformly ergodic Markov chains
• Convergence and consistency of ERM algorithm with uniformly ergodic Markov chain samples
• The generalization performance of ERM algorithm with strongly mixing observations
• Generalization performance of least-square regularized regression algorithm with Markov chain samples

zbMATH Keywords

learning theoryMarkov chainsgeneralization boundsERM algorithmgeometrically ergodic

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Analysis of algorithms (68W40)

Cites Work

• Learning Theory
• Probability Inequalities for Sums of Bounded Random Variables
• On the mathematical foundations of learning
• Title not available (Why is that?)
• Markov chains and stochastic stability
• Sharper bounds for Gaussian and empirical processes
• Title not available (Why is that?)
• Shannon sampling and function reconstruction from point values
• Capacity of reproducing kernel spaces in learning theory
• Rates of convergence for empirical processes of stationary mixing sequences
• Best choices for regularization parameters in learning theory: on the bias-variance problem.
• ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY
• Bounds for the uniform deviation of empirical measures
• New approaches to statistical learning theory
• ONLINE LEARNING WITH MARKOV SAMPLING
• Minimum complexity regression estimation with weakly dependent observations
• SVM Soft Margin Classifiers: Linear Programming versus Quadratic Programming
• Regularized least square regression with dependent samples
• Learning from dependent observations
• Learning and generalisation. With applications to neural networks.
• The generalization performance of ERM algorithm with strongly mixing observations
• Learning rates of regularized regression for exponentially strongly mixing sequence
• The performance bounds of learning machines based on exponentially strongly mixing sequences
• Extension of the PAC framework to finite and countable Markov chains
• An inequality for uniform deviations of sample averages from their means

Cited In (4)

• Generalization bounds of ERM algorithm with Markov chain samples
• Generalization ability of online pairwise support vector machine
• Generalization and Robustness of Batched Weighted Average Algorithm with V-Geometrically Ergodic Markov Data
• Learning from non-irreducible Markov chains

This page was built for publication: Generalization bounds of ERM algorithm with \(V\)-geometrically ergodic Markov chains

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q429786)