Riemannian preconditioning for tensor learning
There are two sets of codes: 1) "tensor completion" which includes polished codes for tensor completion and 2) "tensor regression" which includes polished codes for general tensor regression probelms inluding multilinear multitask learning problems.
The codes are based on the following works.
H. Kasai, P. Jawanpuria, and B. Mishra, “A Riemannian approach to low-rank tensor learning”, published as a chapter in Tensors for Data Processing (978-0-12-824447-0), 2021.
H. Kasai and B. Mishra, “Low-rank tensor completion: a Riemannian manifold preconditioning approach”, ICML, 2016.