English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Sparse-Group Lasso (SGL) has been shown to be a powerful regression techniquefor simultaneously discovering group and within-group sparse patterns by usinga combination of the $\ell_1$ and $\ell_2$ norms. However, in large-scaleapplications, the complexity of the regularizers entails great computationalchallenges. In this paper, we propose a novel Two-Layer Feature REductionmethod (TLFre) for SGL via a decomposition of its dual feasible set. Thetwo-layer reduction is able to quickly identify the inactive groups and theinactive features, respectively, which are guaranteed to be absent from thesparse representation and can be removed from the optimization. Existingfeature reduction methods are only applicable for sparse models with onesparsity-inducing regularizer. To our best knowledge, TLFre is the first onethat is capable of dealing with multiple sparsity-inducing regularizers.Moreover, TLFre has a very low computational cost and can be integrated withany existing solvers. We also develop a screening method---called DPC(DecomPosition of Convex set)---for the nonnegative Lasso problem. Experimentson both synthetic and real data sets show that TLFre and DPC improve theefficiency of SGL and nonnegative Lasso by several orders of magnitude.

Two-Layer Feature Reduction for Sparse-Group Lasso via Decomposition of Convex Sets