Convergence and consistency of ERM algorithm with uniformly ergodic Markov chain samples

DOI10.1142/S0219691316500132zbMath1341.60089OpenAlexW2293967587MaRDI QIDQ2812451

Jie Xu, Xiaomei Mo

Publication date: 16 June 2016

Published in: International Journal of Wavelets, Multiresolution and Information Processing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1142/s0219691316500132

zbMATH Keywords

consistencyconvergence rategeneralization boundempirical risk minimization algorithmuniformly ergodic Markov chain samples

Mathematics Subject Classification ID

Computational methods in Markov chains (60J22) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Numerical analysis or methods applied to Markov chains (65C40)

Cites Work

• Unnamed Item
• Unnamed Item
• Generalization bounds of ERM algorithm with Markov chain samples
• Markov chains and stochastic stability
• General state space Markov chains and MCMC algorithms
• On the Markov chain central limit theorem
• Learning from uniformly ergodic Markov chains
• Best choices for regularization parameters in learning theory: on the bias-variance problem.
• Generalization performance of Gaussian kernels SVMC based on Markov sampling
• On the mathematical foundations of learning

This page was built for publication: Convergence and consistency of ERM algorithm with uniformly ergodic Markov chain samples