Generalization bounds of ERM algorithm with Markov chain samples

DOI10.1007/s10255-011-0096-4zbMath1386.68148OpenAlexW2402905182MaRDI QIDQ403479

Bin Zou, Jie Xu, Zong Ben Xu

Publication date: 29 August 2014

Published in: Acta Mathematicae Applicatae Sinica. English Series (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10255-011-0096-4

zbMATH Keywords

learning theoryuniformly ergodic Markov chaingeneralization boundsERM algorithmrelative uniform convergence

Mathematics Subject Classification ID

Inequalities; stochastic orderings (60E15) Learning and adaptive systems in artificial intelligence (68T05) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20)

Related Items (3)

Learning from non-irreducible Markov chains ⋮ On biased random walks, corrupted intervals, and learning under adversarial design ⋮ Convergence and consistency of ERM algorithm with uniformly ergodic Markov chain samples

Cites Work

• Unnamed Item
• Unnamed Item
• Generalization bounds of ERM algorithm with \(V\)-geometrically ergodic Markov chains
• Markov chains and stochastic stability
• Regularized least square regression with dependent samples
• Learning from dependent observations
• General state space Markov chains and MCMC algorithms
• Learning from uniformly ergodic Markov chains
• Rates of convergence for empirical processes of stationary mixing sequences
• A note on uniform laws of averages for dependent processes
• Learning and generalisation. With applications to neural networks.
• Best choices for regularization parameters in learning theory: on the bias-variance problem.
• New approaches to statistical learning theory
• The generalization performance of ERM algorithm with strongly mixing observations
• Learning rates of regularized regression for exponentially strongly mixing sequence
• Approximation methods for supervised learning
• The performance bounds of learning machines based on exponentially strongly mixing sequences
• Concentration inequalities for dependent random variables via the martingale method
• Weighted sums of certain dependent random variables
• On the mathematical foundations of learning
• Learning Theory
• ONLINE LEARNING WITH MARKOV SAMPLING
• Minimum complexity regression estimation with weakly dependent observations
• ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY
• Extension of the PAC framework to finite and countable Markov chains
• Shannon sampling and function reconstruction from point values

This page was built for publication: Generalization bounds of ERM algorithm with Markov chain samples