Learning Trigonometric Polynomials from Random Samples and Exponential Inequalities for Eigenvalues of Random Matrices

MaRDI QIDQ6478686zbMATH OpenFDO

Authors Karlheinz Gröchenig, B. M. Poetscher, Holger Rauhut

Publication date 26 January 2007

Mathematics Subject Classification ID

Trigonometric polynomials, inequalities, extremal problems (42A05) Sampling theory in information and communication theory (94A20)

Abstract: Motivated by problems arising in random sampling of trigonometric polynomials, we derive exponential inequalities for the operator norm of the difference between the sample second moment matrix $n^{-1}{U}^{\ast }U$ and its expectation where $U$ is a complex random $nimesD$ matrix with independent rows. These results immediately imply deviation inequalities for the largest (smallest) eigenvalues of the sample second moment matrix, which in turn lead to results on the condition number of the sample second moment matrix. We also show that trigonometric polynomials in several variables can be learned from $constcdotDlnD$ random samples.

This page was built for publication: Learning Trigonometric Polynomials from Random Samples and Exponential Inequalities for Eigenvalues of Random Matrices

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6478686)