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

Determining the appropriate batch size for mini-batch gradient descent isalways time consuming as it often relies on grid search. This paper considers aresizable mini-batch gradient descent (RMGD) algorithm based on a multi-armedbandit for achieving best performance in grid search by selecting anappropriate batch size at each epoch with a probability defined as a functionof its previous success/failure. This probability encourages exploration ofdifferent batch size and then later exploitation of batch size with history ofsuccess. At each epoch, the RMGD samples a batch size from its probabilitydistribution, then uses the selected batch size for mini-batch gradientdescent. After obtaining the validation loss at each epoch, the probabilitydistribution is updated to incorporate the effectiveness of the sampled batchsize. The RMGD essentially assists the learning process to explore the possibledomain of the batch size and exploit successful batch size. Experimentalresults show that the RMGD achieves performance better than the best performingsingle batch size. Furthermore, it, obviously, attains this performance in ashorter amount of time than grid search. It is surprising that the RMGDachieves better performance than grid search.

A Resizable Mini-batch Gradient Descent based on a Multi-Armed Bandit