New Algorithms & Models


Multivariate projection techniques are very intuitive methods, but the mathematics behind are somehow complex. As an engineer, I enjoy studying matrix algebra problems with a clear practical application. As a computer scientist, I am especially interested in algorithms. Topics I like include the selection of the number of PCs in PCA, the connection between data and covariance matrices, and with multivariate models, and the development of accurate exploratory data analysis techniques.

One topic I am particularly interested in is the development of sparse multivariate models for omics data: genomics, epigenomics, metagenomics, metabolomics, etc.

Related references: