Hanson-Wright Inequality for Random Tensors under Einstein Product

Shih Yu Chang

Published 2021-11-23, updated 2022-03-01Version 3

The Hanson-Wright inequality is an upper bound for tails of real quadratic forms in independent subgaussian random variables. In this work, we extend the Hanson-Wright inequality for the maximum eigenvalue of the quadratic sum of random Hermitian tensors under Einstein product. We first prove Weyl inequality for tensors under Einstein product and apply this fact to separate the quadratic form of random Hermitian tensors into diagonal sum and coupling (non-diagonal) sum parts. For the diagonal part, we can apply Bernstein inequality to bound the tail probability of the maximum eigenvalue of the sum of independent random Hermitian tensors directly. For coupling sum part, we have to apply decoupling method first, i.e., decoupling inequality to bound expressions with dependent random Hermitian tensors with independent random Hermitian tensors, before applying Bernstein inequality again to bound the tail probability of the maximum eigenvalue of the coupling sum of independent random Hermitian tensors. Finally, the Hanson-Wright inequality for the maximum eigenvalue of the quadratic sum of random Hermitian tensors under Einstein product can be obtained by the combination of the bound from the diagonal sum part and the bound from the coupling (non-diagonal) sum part. In Appendix of this work, we also include the Hanson-Wright inequality under T-product tensor, which can be derived by the same method of establishing the Hanson-Wright inequality under Einstein product except changing the rule of tensors product operation.