English

The Hanson-Wright Inequality for Random Tensors

Probability 2021-06-28 v1

Abstract

We provide moment bounds for expressions of the type (X(1)X(d))TA(X(1)X(d))(X^{(1)} \otimes \dots \otimes X^{(d)})^T A (X^{(1)} \otimes \dots \otimes X^{(d)}) where \otimes denotes the Kronecker product and X(1),,X(d)X^{(1)}, \dots, X^{(d)} are random vectors with independent, mean 0, variance 1, subgaussian entries. The bounds are tight up to constants depending on dd for the case of Gaussian random vectors. Our proof also provides a decoupling inequality for expressions of this type. Using these bounds, we obtain new, improved concentration inequalities for expressions of the form B(X(1)X(d))2\|B (X^{(1)} \otimes \dots \otimes X^{(d)})\|_2.

Keywords

Cite

@article{arxiv.2106.13345,
  title  = {The Hanson-Wright Inequality for Random Tensors},
  author = {Stefan Bamberger and Felix Krahmer and Rachel Ward},
  journal= {arXiv preprint arXiv:2106.13345},
  year   = {2021}
}
R2 v1 2026-06-24T03:34:50.450Z