UCL will host the 3rd workshop on the Theory of Big Data, in June 2017.

Big Data has become ubiquitous in modern society, but drawing insights from it remains a challenge due to its unprecedented degrees of heterogeneity, often compounded by inadequate experimental design. The past decade has seen considerable developments with big data algorithms, but significant challenges remain for the area’s theoretical underpinning.

The aim of this workshop is to gather experts who develop theory and methodology for big data sets; i.e. scientists who construct new algorithms, but also develop theoretical understanding as to the analysis techniques that are optimal or preferable in different sampling scenarios. The workshop will feature research into computational and statistical efficiency trade-offs, high-dimensional dependency structures (such as spatiotemporal models), as well as high-dimensional estimation and learning, and privacy-preserving algorithms.

Focus areas are:

Challenges in Spatial & Temporal Analysis
High-Dimensional Estimation and Learning
Privacy-preserving inference
Tensors and statistical modelling

Contributions for presentations within the broad theme of theoretical, computational and statistical underpinnings of Big Data analysis, emphasizing challenges and opportunities that are not usually found in traditional data analysis problems are welcomed.  Accepted contributions will be designated either 15 minute talks or poster presentations.  Submissions should be made before 14th March 2017 and take the form of an extended abstract (up to 1 side of an A4 sheet) in PDF format, describing the potential contribution, which can be novel or related to an existing pre-print or publication.

For more information please visit www.ucl.ac.uk/bigdata-theory