Classification with non-i.i.d. sampling

DOI10.1016/j.mcm.2011.03.042zbMath1228.62074MaRDI QIDQ652859

Zheng-Chu Guo, Lei Shi

Publication date: 18 December 2011

Published in: Mathematical and Computer Modelling (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.mcm.2011.03.042

zbMATH Keywords

learning theory; reproducing kernel Hilbert spaces; \(\ell ^{2}\)-empirical covering number; \(\beta \)-mixing sequence; capacity dependent error bounds; regularized classification

Mathematics Subject Classification ID

62H30: Classification and discrimination; cluster analysis (statistical aspects)

68T99: Artificial intelligence

46N30: Applications of functional analysis in probability theory and statistics

Related Items

Unnamed Item, ERM scheme for quantile regression, Fast learning from \(\alpha\)-mixing observations

Cites Work

• Unnamed Item
• Unnamed Item
• Learning from non-identical sampling for classification
• Multi-kernel regularized classifiers
• Learning from dependent observations
• Basic properties of strong mixing conditions. A survey and some open questions
• Fast rates for support vector machines using Gaussian kernels
• Rates of convergence for empirical processes of stationary mixing sequences
• A Bennett concentration inequality and its application to suprema of empirical processes
• Learning and generalisation. With applications to neural networks.
• The covering number in learning theory
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• Weak convergence and empirical processes. With applications to statistics
• Least-square regularized regression with non-iid sampling
• Statistical performance of support vector machines
• Learning rates of regularized regression for exponentially strongly mixing sequence
• Learning theory estimates via integral operators and their approximations
• Learning Theory
• Capacity of reproducing kernel spaces in learning theory
• ONLINE LEARNING WITH MARKOV SAMPLING
• Minimum complexity regression estimation with weakly dependent observations
• Improving the sample complexity using global data
• Convexity, Classification, and Risk Bounds