Generalization bounds of ERM algorithm with \(V\)-geometrically ergodic Markov chains
From MaRDI portal
Publication:429786
DOI10.1007/s10444-011-9182-7zbMath1242.68265MaRDI QIDQ429786
Bin Zou, Xiang Yu Chang, Zong Ben Xu
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
68W40: Analysis of algorithms
68T05: Learning and adaptive systems in artificial intelligence
60J10: Markov chains (discrete-time Markov processes on discrete state spaces)
Related Items
Generalization bounds of ERM algorithm with Markov chain samples, Generalization ability of online pairwise support vector machine, Learning from non-irreducible Markov chains
Cites Work
- Unnamed Item
- Unnamed Item
- Markov chains and stochastic stability
- Regularized least square regression with dependent samples
- Learning from dependent observations
- Bounds for the uniform deviation of empirical measures
- Sharper bounds for Gaussian and empirical processes
- Rates of convergence for empirical processes of stationary mixing sequences
- 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
- An inequality for uniform deviations of sample averages from their means
- Learning rates of regularized regression for exponentially strongly mixing sequence
- The performance bounds of learning machines based on exponentially strongly mixing sequences
- On the mathematical foundations of learning
- Learning Theory
- Capacity of reproducing kernel spaces in learning theory
- ONLINE LEARNING WITH MARKOV SAMPLING
- Minimum complexity regression estimation with weakly dependent observations
- ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY
- SVM Soft Margin Classifiers: Linear Programming versus Quadratic Programming
- Extension of the PAC framework to finite and countable Markov chains
- Shannon sampling and function reconstruction from point values
- Probability Inequalities for Sums of Bounded Random Variables
