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

In this paper, we consider a composite difference-of-convex (DC) program,whose objective function is the sum of a smooth convex function with Lipschitzcontinuous gradient, a proper closed and convex function, and a continuousconcave function. This problem has many applications in machine learning anddata science. The proximal DCA (pDCA), a special case of the classical DCA, aswell as two Nesterov-type extrapolated DCA -- ADCA (Phan et al.IJCAI:1369--1375, 2018) and pDCAe (Wen et al. Comput Optim Appl 69:297--324,2018) -- can solve this problem. The algorithmic step-sizes of pDCA, pDCAe, andADCA are fixed and determined by estimating a prior the smoothness parameter ofthe loss function. However, such an estimate may be hard to obtain or poor insome real-world applications. Motivated by this difficulty, we propose avariable metric and Nesterov extrapolated proximal DCA with backtracking(SPDCAe), which combines the backtracking line search procedure (notnecessarily monotone) and the Nesterov's extrapolation for potentialacceleration; moreover, the variable metric method is incorporated for betterlocal approximation. Numerical simulations on sparse binary logistic regressionand compressed sensing with Poisson noise demonstrate the effectiveness of ourproposed method.

A Variable Metric and Nesterov Extrapolated Proximal DCA with Backtracking for A Composite DC Program