High Dimensional Small Data

19 - 20  October 2018

Ca' Foscari, Aula Mario Baratto, Venice (Italy)

Most contemporary large-scale problems in fields such as biology and economics involve a huge number of features that may affect properties and dynamics of the system under study. In order to understand and evaluate the role played by these features in the system’s processes, very large data sets are generally collected, analysed and modelled. Sometimes, however, obtaining data is very costly from an economic, ethical or environmental point of view, and the discovery and analysis of relevant explanatory features must be conducted on small sets of data, indeed the smallest possible. In such situations, fewer experiments mean less resources required, less possible harmful manipulation of living organisms, less polluting effects

The challenge in such cases is how to study high dimensional problems, achieving reliable interpretations and accurate predictions, with a relatively small set of experiments or observations.  The goal of this workshop is to explore different research perspectives and identify modelling opportunities to obtain meaningful information from high dimensional small data (the world of p>>n).


  • Philip J. Brown (University of Kent, UK)
  • Aki Vehtari (Aalto University, FI)
  • Monica Billio (Università Ca’ Foscari, Venezia, IT)
  • Darren Green (GlaxoSmithKline, UK)
  • Martin S. Ridout (University of Kent, UK)
  • Irene Poli (Università Ca’ Foscari, Venezia, IT)
  • Chris Luscombe (GlaxoSmithKline, UK)
  • Oliver Watson (Evariste Technologies Ltd UK)

Workshop committee

  • Philip J Brown (University of Kent, UK)
  • Veronica Distefano (Università Ca’ Foscari, Venezia, IT)
  • Valentina Mameli (Università Ca’ Foscari, Venezia, IT)
  • Irene Poli (Università Ca’ Foscari, Venezia, IT)
  • Debora Slanzi (Università Ca’ Foscari, Venezia, IT)


See the workshop's website for details: High Dimensional Small Data