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.

References in corpus (1)

• Sparse Prediction with the $k$-Support Norm

Cited by in corpus (5)

• The Benefit of Multitask Representation Learning
• Efficient Regularized Piecewise-Linear Regression Trees
• Bounds for Vector-Valued Function Estimation
• New Computational and Statistical Aspects of Regularized Regression with Application to Rare Feature Selection and Aggregation
• A Robust Learning Algorithm for Regression Models Using Distributionally Robust Optimization under the Wasserstein Metric