Application of Parallel Hierarchical Matrices and Low-Rank Tensors in Spatial Statistics and Parameter Identification
Type
PresentationAuthors
Litvinenko, AlexanderKAUST Department
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) DivisionDate
2018-03-12Abstract
Part 1: Parallel H-matrices in spatial statistics- Motivation: improve statistical model
- Tools: Hierarchical matrices
- Matern covariance function and joint Gaussian likelihood
- Identification of unknown parameters via maximizing Gaussian log-likelihood
- Implementation with HLIBPro.
Part 2: Low-rank Tucker tensor methods in spatial statistics
Acknowledgements
KAUSTConference/Event Name
SIAM Conference on Parallel Processing for Scientific ComputingAdditional Links
https://www.siam.org/meetings/pp18/