In recent years the acquisition of big data sets on one hand and the increasing
popularity of high-dimensional models on the other hand have intensified the
interdisciplinary contacts between data sciences, machine learning,
statistics, applied mathematics, computer science and signal processing.
The learning or estimation of patterns and structures from massive observations
in complex models is closely related to the solution of possibly large, ill
posed or ill conditioned inverse problems.
The understanding of graphical and structured models involves
expertise in the algorithmic, numerical and statistical aspects.
Regularisation of ill posed or ill conditioned problems is often based on an
explicit or implicit assumption of sparsity, which can be imposed already at
the recovery of the data, as in compressed sensing.
The goal of this workshop is to bring together several experts in the various
fields of expertise.
- Sparsity (theory, algorithms, applications, ...)
- High-dimensional models
- Inverse problems
- Compressed sensing
- Statistical modelling of high-dimensional data
- Networks and graphical models
- (Medical) Imaging
- Model and variable selection; structured or group selection
- Statistical learning
- Optimization (in sparse/inverse problems or high-dimensional data)
- Algorithms for the above mentioned problems
Laure Blanc-Feraud, Université de Nice-Sophia Antipolis, France
Ivan Markovsky, Vrije Universiteit Brussel, Belgium
Richard Samworth, Cambridge University, UK
Goeran Kauermann, Ludwig-Maximilians-Universität München, Germany
Francesco Stingo, Università degli Studi di Firenze, Italy
Registration is now closed.
As the workshop is free, and the capacity is not unlimited, we kindly yet
firmly ask you to consider registration as a commitment to participate during
the full conference, to cancel participation only for good reasons and in that
case, to inform us as soon as possible at the email address below
The organizers can be contacted at