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

This paper introduces a novel approach to enhance the performance of thestochastic gradient descent (SGD) algorithm by incorporating a modified decaystep size based on $\frac{1}{\sqrt{t}}$. The proposed step size integrates alogarithmic term, leading to the selection of smaller values in the finaliterations. Our analysis establishes a convergence rate of $O(\frac{\lnT}{\sqrt{T}})$ for smooth non-convex functions without thePolyak-{\L}ojasiewicz condition. To evaluate the effectiveness of our approach,we conducted numerical experiments on image classification tasks using theFashionMNIST, and CIFAR10 datasets, and the results demonstrate significantimprovements in accuracy, with enhancements of $0.5\%$ and $1.4\%$ observed,respectively, compared to the traditional $\frac{1}{\sqrt{t}}$ step size. Thesource code can be found at \\\url{https://github.com/Shamaeem/LNSQRTStepSize}.

Modified Step Size for Enhanced Stochastic Gradient Descent: Convergence and Experiments