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 propose an algorithm for optimizing the parameters of single hidden layerneural networks. Specifically, we derive a blockwise difference-of-convex (DC)functions representation of the objective function. Based on the latter, wepropose a block coordinate descent (BCD) approach that we combine with atailored difference-of-convex functions algorithm (DCA). We prove globalconvergence of the proposed algorithm. Furthermore, we mathematically analyzethe convergence rate of parameters and the convergence rate in value (i.e., thetraining loss). We give conditions under which our algorithm converges linearlyor even faster depending on the local shape of the loss function. We confirmour theoretical derivations numerically and compare our algorithm againststate-of-the-art gradient-based solvers in terms of both training loss and testloss.

A Globally Convergent Algorithm for Neural Network Parameter Optimization Based on Difference-of-Convex Functions