A chain rule for the expected suprema of Gaussian processes

DOI10.1016/J.TCS.2016.07.034MaRDI QIDQ329618zbMATHOpenAlexFDO

Authors Andreas Maurer

Publication date 21 October 2016

Published in Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.tcs.2016.07.034

zbMATH Keywords

empirical processeschain rulegeneralizationmulti-layers

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Gaussian processes (60G15) Random fields (60G60) Extreme value theory; extremal stochastic processes (60G70)

Recommendations

• A chain rule for the expected suprema of Gaussian processes
• Chaining and the geometry of stochastic processes
• The Generic Chaining
• Bounds for the expected supremum of some non-stationary Gaussian processes
• Bounding the expectation of the supremum of an empirical process over a (weak) VC-major class

Cites work

• scientific article; zbMATH DE number 5957307 (Why is no real title available?)
• scientific article; zbMATH DE number 1113195 (Why is no real title available?)
• scientific article; zbMATH DE number 1552503 (Why is no real title available?)
• scientific article; zbMATH DE number 1448976 (Why is no real title available?)
• $K$-Dimensional Coding Schemes in Hilbert Spaces
• 10.1162/153244303321897690
• 10.1162/1532443041424300
• A simple proof of the majorizing measure theorem
• Bounds for linear multi-task learning
• Characterization of the law of the iterated logarithm in Banach spaces
• Concentration inequalities. A nonasymptotic theory of independence
• Majorizing measures without measures
• Neural Network Learning
• Regularity of Gaussian processes
• Regularization techniques for learning with matrices
• The Generic Chaining
• Transfer bounds for linear feature learning
• \(\ell\)-norm and its application to learning theory

Cited in

(4)

• A chain rule for the expected suprema of Gaussian processes
• V.N. Sudakov’s Work on Expected Suprema of Gaussian Processes
• Expected supremum of a random linear combination of shifted kernels
• Local Rademacher complexity-based learning guarantees for multi-task learning

This page was built for publication: A chain rule for the expected suprema of Gaussian processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q329618)