Tensorized Random Projections
[edit]
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, PMLR 108:33063316, 2020.
Abstract
We introduce a novel random projection technique for efficiently reducing the dimension of very highdimensional tensors. Building upon classical results on Gaussian random projections and JohnsonLindenstrauss transforms (JLT), we propose two tensorized random projection maps relying on the tensor train (TT) and CP decomposition format, respectively. The two maps offer very low memory requirements and can be applied efficiently when the inputs are low rank tensors given in the CP or TT format.Our theoretical analysis shows that the dense Gaussian matrix in JLT can be replaced by a lowrank tensor implicitly represented in compressed form with random factors, while still approximately preserving the Euclidean distance of the projected inputs. In addition, our results reveal that the TT format is substantially superior to CP in terms of the size of the random projection needed to achieve the same distortion ratio. Experiments on synthetic data validate our theoretical analysis and demonstrate the superiority of the TT decomposition.
Related Material


