Rank Bounds for Approximating Gaussian Densities in the Tensor-Train Format

Paul B. Rohrbach, Sergey Dolgov, Lars Grasedyck, Robert Scheichl

Research output: Contribution to journalArticlepeer-review

5 Downloads (Pure)


Low rank tensor approximations have been employed successfully, for example, to build surrogate models that can be used to speed up large-scale inference problems in high dimensions. The success of this depends critically on the rank that is necessary to represent or approximate the underlying distribution. In this paper, we develop a-priori rank bounds for approximations in the functional Tensor-Train representation for the case of a Gaussian (normally distributed) model. We show that under suitable conditions on the precision matrix, we can represent the Gaussian density to high accuracy without suffering from an exponential growth of complexity as the dimension increases. Our results provide evidence of the suitability and limitations of low rank tensor methods in a simple but important model case. Numerical experiments confirm that the rank bounds capture the qualitative behavior of the rank structure when varying the parameters of the precision matrix and the accuracy of the approximation.
Original languageEnglish
Pages (from-to)1191-1224
Number of pages34
JournalSIAM/ASA Journal on Uncertainty Quantification
Issue number3
Early online date28 Sep 2022
Publication statusPublished - 30 Sep 2022


  • math.NA
  • cs.NA
  • math.ST
  • stat.TH
  • 15A23, 15A69, 65C60, 65D32, 65D15, 41A10


Dive into the research topics of 'Rank Bounds for Approximating Gaussian Densities in the Tensor-Train Format'. Together they form a unique fingerprint.

Cite this