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

The overall execution time of distributed matrix computations is oftendominated by slow worker nodes (stragglers) within the clusters. Recently,different coding techniques have been utilized to mitigate the effect ofstragglers where worker nodes are assigned the job of processing encodedsubmatrices of the original matrices. In many machine learning or optimizationproblems the relevant matrices are often sparse. Several prior codedcomputation methods operate with dense linear combinations of the originalsubmatrices; this can significantly increase the worker node computation timesand consequently the overall job execution time. Moreover, several existingtechniques treat the stragglers as failures (erasures) and discard theircomputations. In this work, we present a coding approach which operates withlimited encoding of the original submatrices and utilizes the partialcomputations done by the slower workers. While our scheme can continue to havethe optimal threshold of prior work, it also allows us to trade off thestraggler resilience with the worker computation speed for sparse inputmatrices. Extensive numerical experiments done in AWS (Amazon Web Services)cluster confirm that the proposed approach enhances the speed of the workercomputations (and thus the whole process) significantly.

A Unified Treatment of Partial Stragglers and Sparse Matrices in Coded Matrix Computation