Results 1 
7 of
7
Dynamic Compressive Sensing: SPARSE RECOVERY ALGORITHMS FOR STREAMING SIGNALS AND VIDEO
, 2013
"... ..."
SparsityAware Learning and Compressed Sensing: An Overview
, 2014
"... The notion of regularization has been widely used as a tool to address a number of problems that are usually encountered in Machine Learning. Improving the performance of an estimator by shrinking the norm of the MVU estimator, guarding against overfitting, coping with illconditioning, provid ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
The notion of regularization has been widely used as a tool to address a number of problems that are usually encountered in Machine Learning. Improving the performance of an estimator by shrinking the norm of the MVU estimator, guarding against overfitting, coping with illconditioning, provid
Figure 1: Proof flowchart for the Sparse Coding Stability Theorem (Theorem 4).
"... The flow of this section is as follows. We first establish some preliminary notation and summarize important conditions. Several lemmas are then presented to support a key sparsity lemma. This sparsity lemma establishes that the solution to the perturbed problem is sparse provided the perturbation i ..."
Abstract
 Add to MetaCart
(Show Context)
The flow of this section is as follows. We first establish some preliminary notation and summarize important conditions. Several lemmas are then presented to support a key sparsity lemma. This sparsity lemma establishes that the solution to the perturbed problem is sparse provided the perturbation is not too large. Finally, the sparsity of this new solution is exploited to bound the difference of the new solution from the old solution. This flow is embodied by the proof flowchart in Figure 1.