Optimal rate for support vector machine regression with Markov chain samples

DOI10.1142/S0219691314500453zbMath1327.68201OpenAlexW2116231267MaRDI QIDQ5248169

Jie Xu

Publication date: 27 April 2015

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/s0219691314500453

zbMATH Keywords

uniformly ergodic Markov chainoptimal ratesupport vector machine regression (SVMR)

Mathematics Subject Classification ID

Sampling theory, sample surveys (62D05) Markov processes: estimation; hidden Markov models (62M05) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (2)

The consistency of least-square regularized regression with negative association sequence ⋮ Coefficient-based regularized regression with dependent and unbounded sampling

Cites Work

• Unnamed Item
• Fast rates for support vector machines using Gaussian kernels
• Analysis of support vector machines regression
• 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.
• Concentration of measure inequalities for Markov chains and \(\Phi\)-mixing processes.
• The covering number in learning theory
• A measure concentration inequality for contracting Markov chains
• The generalization performance of ERM algorithm with strongly mixing observations
• Regularization networks and support vector machines
• Generalization performance of Gaussian kernels SVMC based on Markov sampling
• Learning rates of regularized regression for exponentially strongly mixing sequence
• Learning rates of least-square regularized regression
• On the mathematical foundations of learning
• Capacity of reproducing kernel spaces in learning theory
• ONLINE LEARNING WITH MARKOV SAMPLING
• Minimum complexity regression estimation with weakly dependent observations
• The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network
• Uniform ergodicity and strong mixing

This page was built for publication: Optimal rate for support vector machine regression with Markov chain samples