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

In the realm of unsupervised learning, Bayesian nonparametric mixture models,exemplified by the Dirichlet Process Mixture Model (DPMM), provide a principledapproach for adapting the complexity of the model to the data. Such models areparticularly useful in clustering tasks where the number of clusters isunknown. Despite their potential and mathematical elegance, however, DPMMs haveyet to become a mainstream tool widely adopted by practitioners. This isarguably due to a misconception that these models scale poorly as well as thelack of high-performance (and user-friendly) software tools that can handlelarge datasets efficiently. In this paper we bridge this practical gap byproposing a new, easy-to-use, statistical software package for scalable DPMMinference. More concretely, we provide efficient and easily-modifiableimplementations for high-performance distributed sampling-based inference inDPMMs where the user is free to choose between either a multiple-machine,multiple-core, CPU implementation (written in Julia) and a multiple-stream GPUimplementation (written in CUDA/C++). Both the CPU and GPU implementations comewith a common (and optional) python wrapper, providing the user with a singlepoint of entry with the same interface. On the algorithmic side, ourimplementations leverage a leading DPMM sampler from (Chang and Fisher III,2013). While Chang and Fisher III's implementation (written in MATLAB/C++) usedonly CPU and was designed for a single multi-core machine, the packages weproposed here distribute the computations efficiently across either multiplemulti-core machines or across mutiple GPU streams. This leads to speedups,alleviates memory and storage limitations, and lets us fit DPMMs tosignificantly larger datasets and of higher dimensionality than was possiblepreviously by either (Chang and Fisher III, 2013) or other DPMM methods.

CPU- and GPU-based Distributed Sampling in Dirichlet Process Mixtures for Large-scale Analysis