We present a data dependent generalization bound for a large class of
regularized algorithms which implement structured sparsity constraints. The
bound can be applied to standard squared-norm regularization, the Lasso, the
group Lasso, some versions of the group Lasso with overlapping groups, multiple
kernel learning and other regularization schemes. In all these cases
competitive results are obtained. A novel feature of our bound is that it can
be applied in an infinite dimensional setting such as the Lasso in a separable
Hilbert space or multiple kernel learning with a countable number of kernels.

本文介绍了一种基于数据相关性的一般化界限，适用于许多实现了结构稀疏性限制的正则化算法。该界限可以应用于标准的平方范数正则化、套索 (Lasso)、组套索 (group Lasso)、一些具有重叠组的组套索版本、多核学习 (multiple kernel learning) 和其他正则化方案。在所有这些情况下，都可以获得有竞争力的结果。我们界限的新特点是，它可以应用于无限维度的设置，例如具有可分离的希尔伯特空间的套索 (Lasso) 或具有可数核的多核学习 (multiple kernel learning)。