Reconstruction and Subgaussian Operators in Asymptotic Geometric Analysis

By Shahar Mendelson, Alain Pajor, Nicole Tomczak-Jaegermann. 2007

233 citations recorded by the source corpus.

Subfields: Applied Mathematics, Computational Mechanics, Computer Graphics and Computer-Aided Design

View Paper: https://www.semanticscholar.org/paper/edf558b234f74c032ba1cb700be6441daeec35ec

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Applied Mathematics

In Computational Mechanics

In Computer Graphics and Computer-Aided Design

Citations in the corpus

A Simple Proof of the Restricted Isometry Property for Random Matrices (2008, background): “It was not until quite recently that it was understood that the Bernoulli processes also yield the upper bound in (2.3) [17, 19].”
Introduction to the non-asymptotic analysis of random matrices (2010, background): “5 Sub-gaussian distributions in R are well studied in geometric functional analysis; see [53] for a link with compressed sensing.”
Rejoinder: Local Rademacher complexities and oracle inequalities in risk minimization (2006, background): “There has been very interesting recent work on mathematical justification of this approach in several settings (see [2, 3, 4, 5, 6, 10, 11]).”
Local Rademacher complexities and oracle inequalities in risk minimization (2006, background): “, the ψα metrics) will play a central role in such a development, as in [7, 8].”
Oracle inequalities in empirical risk minimization and sparse recovery problems (2011, methodology): “421; Mendelson, Pajor and Tomczak-Jaegermann [78], Lemma 3.”
Aggregation via empirical risk minimization (2009, methodology): “Nevertheless, it is possible to obtain similar results under milder assumptions on Y and F , using the methods developed in [9,18,19] for handling empirical processes indexed by powers of unbounded function classes that satisfy suitable tail assumptions.”
Group Lasso for high dimensional sparse quantile regression models (2011, background): “The proof of Lemma 3.3 relies on a result from geometric functional analysis (Mendelson et al., 2007).”
Iterative Hard Thresholding for Compressed Sensing (2008, background): “The importance of thesep-compressiblesignals is that they can be well approximated using exact sparse signals.”