Statistical methodology and theory for functional and topological data. Abstracts from the workshop held June 16–22, 2019. (English) Zbl 1439.00059

Delaigle, Aurore (ed.); Meister, Alexander (ed.); Panaretos, Victor M. (ed.); Wasserman, Larry (ed.)

Oberwolfach Rep. 16, No. 2, 1697-1735 (2019).

Summary: The workshop focuses on the statistical analysis of complex data which cannot be represented as realizations of finite-dimensional random vectors. An example of such data are functional data. They arise in a variety of climate, biological, medical, physical and engineering problems, where the observations can be represented by curves and surfaces. Fast advances in technology continuously produce a deluge of bigger data with even more complex structures such as arteries in the brain, bones of a human body or social networks. This has sparked enormous interest in more general statistical problems where the random observations are elements of abstract topological spaces.
The workshop will stimulate development of new statistical methods for these types of data and will be an ideal platform for discussing their theoretical properties (e.g. asymptotic optimality), computational performance, and new exciting applications in areas such as machine learning, image analysis, biometrics and econometrics.

MSC:

00B05	Collections of abstracts of lectures
00B25	Proceedings of conferences of miscellaneous specific interest
62-06	Proceedings, conferences, collections, etc. pertaining to statistics
62Hxx	Multivariate analysis
62Mxx	Inference from stochastic processes
62Rxx	Statistics on algebraic and topological structures

References:

[1]	Bai, Z. D. and Silverstein, J. W.(2004). CLT for linear spectral statistics of large dimensional sample covariance matrices.Annals of Probability32, 553-605. · Zbl 1063.60022
[2]	El Karoui, N.