Generalization bounds of ERM algorithm with Markov chain samples
DOI10.1007/S10255-011-0096-4zbMATH Open1386.68148OpenAlexW2402905182MaRDI QIDQ403479FDOQ403479
Authors: Bin Zou, Jie Xu, Zongben 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
Recommendations
- Learning from uniformly ergodic Markov chains
- Generalization bounds of ERM algorithm with \(V\)-geometrically 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
learning theoryuniformly ergodic Markov chaingeneralization boundsERM algorithmrelative uniform convergence
Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Learning and adaptive systems in artificial intelligence (68T05) Inequalities; stochastic orderings (60E15)
Cites Work
- Learning Theory
- On the mathematical foundations of learning
- Title not available (Why is that?)
- Markov chains and stochastic stability
- General state space Markov chains and MCMC algorithms
- Support vector machine soft margin classifiers: error analysis
- Approximation methods for supervised learning
- Weighted sums of certain dependent random variables
- Shannon sampling and function reconstruction from point values
- 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
- New approaches to statistical learning theory
- ONLINE LEARNING WITH MARKOV SAMPLING
- Minimum complexity regression estimation with weakly dependent observations
- Regularized least square regression with dependent samples
- Learning from dependent observations
- Concentration inequalities for dependent random variables via the martingale method
- Learning and generalisation. With applications to neural networks.
- Learning from uniformly ergodic Markov chains
- A note on uniform laws of averages for dependent processes
- 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
- Generalization bounds of ERM algorithm with \(V\)-geometrically ergodic Markov chains
- Extension of the PAC framework to finite and countable Markov chains
Cited In (8)
- Generalization bounds of ERM algorithm with \(V\)-geometrically ergodic Markov chains
- ERM learning with unbounded sampling
- Learning from uniformly ergodic Markov chains
- The generalization performance of ERM algorithm with strongly mixing observations
- Convergence and consistency of ERM algorithm with uniformly ergodic Markov chain samples
- Generalization performance of least-square regularized regression algorithm with Markov chain samples
- Learning from non-irreducible Markov chains
- On biased random walks, corrupted intervals, and learning under adversarial design
This page was built for publication: Generalization bounds of ERM algorithm with Markov chain samples
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q403479)
