# Sample, computation vs storage tradeoffs for classification using tensor subspace models

arXiv: https://arxiv.org/abs/1706.05599 · HTML: https://mlsanity.com/paper/1706.05599/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jun 2017.

## Built on by (most cited first, 2 of 2)

- [Tensor PCA from basis in tensor space](https://mlsanity.com/paper/2305.02803/) (2023)
- [Decomposition of linear tensor transformations](https://mlsanity.com/paper/2309.07819/) (2023)

## Abstract (arXiv)

In this paper, we exhibit the tradeoffs between the (training) sample, computation and storage complexity for the problem of supervised classification using signal subspace estimation. Our main tool is the use of tensor subspaces, i.e. subspaces with a Kronecker structure, for embedding the data into lower dimensions. Among the subspaces with a Kronecker structure, we show that using subspaces with a hierarchical structure for representing data leads to improved tradeoffs. One of the main reasons for the improvement is that embedding data into these hierarchical Kronecker structured subspaces prevents overfitting at higher latent dimensions.