Probabilistic Graphical Models on Multi-Core CPUs using Java 8

TL;DR

This paper explores how to efficiently implement probabilistic graphical models on multi-core CPUs using Java 8's functional programming features, focusing on parallel algorithms for inference and learning.

Contribution

It introduces parallelization techniques for PGMs using Java 8, including data structures and algorithms, demonstrated with the AMIDST toolbox.

Findings

Parallel algorithms improve computational efficiency on multi-core CPUs.

Java 8 features facilitate seamless parallel processing of PGMs.

Experimental results validate the effectiveness of the proposed methods.

Abstract

In this paper, we discuss software design issues related to the development of parallel computational intelligence algorithms on multi-core CPUs, using the new Java 8 functional programming features. In particular, we focus on probabilistic graphical models (PGMs) and present the parallelisation of a collection of algorithms that deal with inference and learning of PGMs from data. Namely, maximum likelihood estimation, importance sampling, and greedy search for solving combinatorial optimisation problems. Through these concrete examples, we tackle the problem of defining efficient data structures for PGMs and parallel processing of same-size batches of data sets using Java 8 features. We also provide straightforward techniques to code parallel algorithms that seamlessly exploit multi-core processors. The experimental analysis, carried out using our open source AMIDST (Analysis of MassIve Data STreams) Java toolbox, shows the merits of the proposed solutions.