Presentations, by author
Group photo (jpg)
Information for presenters
Joining instructions (pdf)
Sparse structures: statistical theory and practice
Research workshop: 16-18 June 2010, Bristol, UK
One of the most challenging problems in modern statistics is to find effective methods for the analysis of complex multi-dimensional data. Sparsity has been emerging as a major tool for handling statistical problems in high dimensions.
However, the development of sparse methodology has been running in two different directions. On one hand, for example, theoretical properties of lasso-type estimators have been studied extensively, and new types of methods have been proposed giving sparse estimators with good properties; however, little is known about how relevant they are to real life problems. And on the other hand, there are efficient algorithms, many based on Bayesian models, which apparently work well in practice, but since little is known about their theoretical properties, nothing mathematical can be said about how well they might work in general.
The aim of the workshop is to bring together theory and practice in modelling high-dimensional data; we hope to encourage genuine interaction between proponents of different approaches. We anticipate coming to a better understanding of the possibilities for finding robust rigorously-founded methods, well-tuned to the demands of data arising in various important application domains, whose theoretical properties can be precisely documented.
The workshop will be held in Bristol, UK, from 16 to 18 June 2010; the programme will begin on the Wednesday morning, and finish late afternoon on Friday. The workshop will feature about 12 invited speakers, and a contributed and poster programme. Participants are strongly encouraged to travel to Bristol on Tuesday 15 June, and to stay over to Saturday 19 June before returning, so as not to miss the final session which we plan to be a panel discussion centred around the invited speakers.
The workshop is being organised by Natalia Bochkina (Edinburgh) and Li Chen and Peter Green, with Azita Ghassemi (Bristol).