Hanson-Wright Inequality for Random Tensors under Einstein Product
Shih Yu Chang

TL;DR
This paper extends the Hanson-Wright inequality to the maximum eigenvalue of quadratic sums of random Hermitian tensors under Einstein product, using Weyl inequality, decoupling, and Bernstein bounds.
Contribution
It introduces a novel Hanson-Wright inequality for random Hermitian tensors under Einstein product, including a Weyl inequality and a decoupling approach.
Findings
Established Hanson-Wright inequality for Einstein product tensors.
Derived bounds for maximum eigenvalues of quadratic sums of random tensors.
Included extension to T-product tensors in the appendix.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTensor decomposition and applications · Advanced Neuroimaging Techniques and Applications · Sparse and Compressive Sensing Techniques
