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

Optimizing with group sparsity is significant in enhancing modelinterpretability in machining learning applications, e.g., feature selection,compressed sensing and model compression. However, for large-scale stochastictraining problems, effective group sparsity exploration are typically hard toachieve. Particularly, the state-of-the-art stochastic optimization algorithmsusually generate merely dense solutions. To overcome this shortage, we proposea stochastic method -- Half-space Stochastic Projected Gradient (HSPG) methodto search solutions of high group sparsity while maintain the convergence.Initialized by a simple Prox-SG Step, the HSPG method relies on a novelHalf-Space Step to substantially boost the sparsity level. Numerically, HSPGdemonstrates its superiority in deep neural networks, e.g., VGG16, ResNet18 andMobileNetV1, by computing solutions of higher group sparsity, competitiveobjective values and generalization accuracy.

Half-Space Proximal Stochastic Gradient Method for Group-Sparsity Regularized Problem