This course will give a detailed introduction to learning theory with a focus on the classification problem. It will be shown how to obtain (pobabilistic) bounds on the generalization error for certain types of algorithms. The main themes will be: * probabilistic inequalities and concentration inequalities * union bounds, chaining * measuring the size of a function class, Vapnik Chervonenkis dimension, shattering dimension and Rademacher averages * classification with real-valued functions Some knowledge of probability theory would be helpful but not required since the main tools will be introduced.
J. Helton, T. Mai, and R. Speicher. (2015)cite arxiv:1511.05330Comment: We have undertaken a major revision, mainly for the sake of clarity and readability.
K. Kawaguchi, L. Kaelbling, and Y. Bengio. (2017)cite arxiv:1710.05468Comment: To appear in Mathematics of Deep Learning, Cambridge University Press. All previous results remain unchanged.
M. Raginsky, and I. Sason. (2012)cite arxiv:1212.4663Comment: Foundations and Trends in Communications and Information Theory, vol. 10, no 1-2, pp. 1-248, 2013. Second edition was published in October 2014. ISBN to printed book: 978-1-60198-906-2.