Regularization and the small-ball method. I: Sparse recovery (Q1750281): Difference between revisions
From MaRDI portal
Set profile property. |
Changed an Item |
||
Property / arXiv ID | |||
Property / arXiv ID: 1601.05584 / rank | |||
Normal rank |
Revision as of 22:39, 18 April 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Regularization and the small-ball method. I: Sparse recovery |
scientific article |
Statements
Regularization and the small-ball method. I: Sparse recovery (English)
0 references
18 May 2018
0 references
Let \((\Omega, \mu)\) be a probability space and set \(X\) to be distributed according to \(\mu\). \(F\) is a class of real-valued functions defined on \(\Omega\), \(Y\) is the unknown random variable that one would like to approximate using function in \(F\) and \(\lambda\) is the regularization parameter. The authors discuss the best approximation to \(y\) and find the function \(f^*\) that minimizes in \(F\) the squared loss functional \(f\to E(f(x)-y)^2\).
0 references
empirical processes
0 references
high dimensional statistics
0 references