Robust and Efficient Solutions to the "Big Data" Challenge

The present "Big Data" era is characterized by the sheer amount and variety of available information. Statisticians and data scientists are challenged to deal with high-dimensional data, complicated dependence structures, or data taking values on non-flat surfaces such as a sphere or a cylinder.
More than ever this calls for new methodologies and the literature on these topics grew exponentially fast in the last decade. All too often, however, the practical applicability of the proposed techniques is jeopardized by the stringent restrictions placed on the number of variables at hand, on the type of dependence allowed in the data, or on the assumed distribution of the data. The objective of this project is to develop methods that can address the challenges of "Big Data" robustly, efficiently, and without such restrictive assumptions.


Davy Paindaveine
European Centre for Advanced Research in Economics and Statistics (ECARES, Solvay Business School of Economics & Management)
Department of Mathematics (Faculty of Sciences)


David Preinerstorfer, ECARES (Solvay Business School of Economics & Management)
Thomas Verdebout, Department of Mathematics (Faculty of Sciences)

Created on September 5, 2018