Sharp Injective Norm Bounds for Inhomogeneous Gaussian Tensors and Sparse Extensions
Abstract
We study the Euclidean injective norm of inhomogeneous random tensors with independent entries. For Gaussian tensors, we establish optimal two-sided bounds for the expected norm, with constants depending only on the tensor order. These bounds describe the interplay between variance accumulation along fibres and the contribution of the largest individual entries. In the matrix case, our result is consistent with the characterizations in~\cite{LVHY18}. We then extend the analysis to sparse Gaussian tensors with arbitrary amplitudes and activation probabilities. The expected norm is characterized by the expected largest absolute entry and the largest fibre standard deviation after truncating amplitudes at this scale. Our proofs combine geometric chaining with estimates for averaging over the random support.
Related
- Upper Bounds on the Strassen CP Rank Gap and Symmetric Rank Gap of Third-Order Tensors
- M-Eigenpairs of Partially Symmetric Tensors: Exact Reformulation and Perturbation Bounds
- Local increment inference for time-inhomogeneous drift in Gaussian processes
- Caffarelli-Kohn-Nirenberg and Weighted Gaussian Poincaré Inequalities: a complete characterization of sharp L2 stability and Lp extensions
- Upper Bounds on the Comon Rank Gap of Real Symmetric Third-Order Tensors
BibTeX
@misc{dai2026sharp,
title = {{Sharp Injective Norm Bounds for Inhomogeneous Gaussian Tensors and Sparse Extensions}},
author = {Guozheng Dai and Ke Wang},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.02813},
eprint = {2611.02813},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.02813},
}
RIS
TY - UNPB
TI - Sharp Injective Norm Bounds for Inhomogeneous Gaussian Tensors and Sparse Extensions
AU - Guozheng Dai
AU - Ke Wang
PY - 2026
DA - 2026/11/02
PB - arXiv
DO - 10.48550/arxiv.2611.02813
UR - https://arxiv.org/abs/2611.02813
AB - We study the Euclidean injective norm of inhomogeneous random tensors with independent entries. For Gaussian tensors, we establish optimal two-sided bounds for the expected norm, with constants depending only on the tensor order. These bounds describe the interplay between variance accumulation along fibres and the contribution of the largest individual entries. In the matrix case, our result is consistent with the characterizations in~\cite{LVHY18}. We then extend the analysis to sparse Gaussian tensors with arbitrary amplitudes and activation probabilities. The expected norm is characterized by the expected largest absolute entry and the largest fibre standard deviation after truncating amplitudes at this scale. Our proofs combine geometric chaining with estimates for averaging over the random support.
ER -