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

We study stochastic convex optimization subjected to linear equalityconstraints. Traditional Stochastic Alternating Direction Method of Multipliersand its Nesterov's acceleration scheme can only achieve ergodic O(1/\sqrt{K})convergence rates, where K is the number of iteration. By introducing VarianceReduction (VR) techniques, the convergence rates improve to ergodic O(1/K). Inthis paper, we propose a new stochastic ADMM which elaborately integratesNesterov's extrapolation and VR techniques. We prove that our algorithm canachieve a non-ergodic O(1/K) convergence rate which is optimal for separablelinearly constrained non-smooth convex problems, while the convergence rates ofVR based ADMM methods are actually tight O(1/\sqrt{K}) in non-ergodic sense. Tothe best of our knowledge, this is the first work that achieves a trulyaccelerated, stochastic convergence rate for constrained convex problems. Theexperimental results demonstrate that our algorithm is significantly fasterthan the existing state-of-the-art stochastic ADMM methods.

Faster and Non-ergodic O(1/K) Stochastic Alternating Direction Method of Multipliers