Relational learning can be used to augment one data source with other correlated sources of information, to improve predictive accuracy. We frame a large class of relational learning problems as matrix factorization problems, and propose a hierarchical Bayesian model. Training our Bayesian model using random-walk Metropolis-Hastings is impractically slow, and so we develop a block Metropolis-Ha...

Functional brain imaging produces huge amounts of data, of which only a fraction are analyzed. Existing univariate and multivariate analyses of brain activity ignore interactions between regions, and analyses of interactions (functional connectivity) are typically biased toward regions of interest chosen based on their activity profile. This technical report provides a provisional description o...

We investigate the scheduling of matrix computations expressed as directed acyclic graphs for shared-memory parallelism. Because of the data granularity in this problem domain, even slight variations in load balance or data locality can greatly affect performance. Well-known scheduling algorithms such as work stealing have proven time and space bounds, but these bounds do not provide a discerna...

Sparse matrix vector multiplication (SpMxV) is often one of the core components of many scientific applications. Many authors have proposed methods for its data distribution in distributed memory multiprocessors. We can classify these into four groups: Scatter, D-Way Strip, Recursive and Miscellaneous. In this work we propose a new method (Multiple Recursive Decomposition (MRD)), which partitio...

Integer datasets frequently appear in many applications in science and engineering. To analyze these datasets, we consider an integer matrix approximation technique that can preserve the original dataset characteristics. Because integers are discrete in nature, to the best of our knowledge, no previously proposed technique developed for real numbers can be successfully applied. In this study, w...

The data validation consists in obtaining an estimation of the true values of process variables that respect the balance equations. Generally, the procedure needs the knowledge of the variance of the measurement errors; unfortunately, in most situations, we only have a rough estimation of this variance and therefore the data validation procedure gives results depending on this poor estimation. ...

In this note we show how the entries of a data matrix can be approximated by a sum of row effects, column effects and interaction terms in a robust way using a weighted L1 estimator. We discuss an algorithm to compute this fit, and show by a simulation experiment and an example that the proposed method can be a useful tool in exploring data matrices. Moreover, a robust biplot is produced as a b...

Motivation: Gene expression data consists of expression level reads for thousands of genes across dozens of experimental conditions, time points, cell types or repeated experiments. The goal of unsupervised modeling of such data is to find some underlying organization, structure or redundancy in the data, such as similarity or dependency between genes or between experiments. Such structure can ...

This paper introduces a novel method based on auxiliary matrix to hide a text data in an RGB plane. To hide the data in RGB planes of image via scanning, encryption and decryption. To enhance the security, the scanning technique combines two different traversals – spiral and snake traversal. The encryption algorithm involves auxiliary matrix as a payload and consider the least significant bits ...