HIGHLIGHTS
- who: Tensor Train et al. from the School of Information and Technology, ShanghaiTech University, Shanghai, China have published the paper: Computer Modeling in, in the Journal: (JOURNAL)
- what: This work proposes a (TTRP) method for dimension reduction where pairwise distances can be approximately preserved. The authors provide a theoretical analysis of the bias and the variance of TTRP which shows that this approach is an expected isometric with bounded variance and the authors show that the scaling Rademacher variable is an optimal choice for generating the corresponding TT-cores. The authors focus on the low . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.