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

One of the most efficient methods to solve L2-regularized primal problems,such as logistic regression and linear support vector machine (SVM)classification, is the widely used trust region Newton algorithm, TRON. WhileTRON has recently been shown to enjoy substantial speedups on shared-memorymulti-core systems, exploiting graphical processing units (GPUs) to speed upthe method is significantly more difficult, owing to the highly complex andheavily sequential nature of the algorithm. In this work, we show that usingjudicious GPU-optimization principles, TRON training time for different lossesand feature representations may be drastically reduced. For sparse featuresets, we show that using GPUs to train logistic regression classifiers inLIBLINEAR is up to an order-of-magnitude faster than solely usingmultithreading. For dense feature sets--which impose far more stringent memoryconstraints--we show that GPUs substantially reduce the lengthy SVM learningtimes required for state-of-the-art proteomics analysis, leading to dramaticimprovements over recently proposed speedups. Furthermore, we show how GPUspeedups may be mixed with multithreading to enable such speedups when thedataset is too large for GPU memory requirements; on a massive dense proteomicsdataset of nearly a quarter-billion data instances, these mixed-architecturespeedups reduce SVM analysis time from over half a week to less than a singleday while using limited GPU memory.

GPU-Accelerated Primal Learning for Extremely Fast Large-Scale Classification