An Inequality with Applications to Structured Sparsity and Multitask Dictionary Learning
Abstract
From concentration inequalities for the suprema of Gaussian or Rademacher processes an inequality is derived. It is applied to sharpen existing and to derive novel bounds on the empirical Rademacher complexities of unit balls in various norms appearing in the context of structured sparsity and multitask dictionary learning or matrix factorization. A key role is played by the largest eigenvalue of the data covariance matrix.
Cite
Text
Maurer et al. "An Inequality with Applications to Structured Sparsity and Multitask Dictionary Learning." Annual Conference on Computational Learning Theory, 2014.Markdown
[Maurer et al. "An Inequality with Applications to Structured Sparsity and Multitask Dictionary Learning." Annual Conference on Computational Learning Theory, 2014.](https://mlanthology.org/colt/2014/maurer2014colt-inequality/)BibTeX
@inproceedings{maurer2014colt-inequality,
title = {{An Inequality with Applications to Structured Sparsity and Multitask Dictionary Learning}},
author = {Maurer, Andreas and Pontil, Massimiliano and Romera-Paredes, Bernardino},
booktitle = {Annual Conference on Computational Learning Theory},
year = {2014},
pages = {440-460},
url = {https://mlanthology.org/colt/2014/maurer2014colt-inequality/}
}