Learning high-dimensional functions with tree-based tensor formats

Vortrag von Prof. Dr. Anthony Nouy

Datum: 06.12.17  Zeit: 16.15 - 17.15  Raum: ETH HG E 1.2

Tensor methods are among the most prominent tools for the approximation of high-dimensional functions. Such approximation problems naturally arise in statistical learning, stochastic analysis and uncertainty quantification. In many practical situations, the approximation of high-dimensional functions is made computationally tractable by using rank-structured approximations. In this talk, we give an introduction to tree-based (hierarchical) tensor formats and then present adaptive algorithms for the approximation in these formats using statistical methods.