The Hanson-Wright inequality for random tensors

DOI10.1007/S43670-022-00028-4zbMATH Open1495.60003arXiv2106.13345OpenAlexW3177155849WikidataQ114215885 ScholiaQ114215885MaRDI QIDQ2164658FDOQ2164658

Authors: Stefan Bamberger, Felix Krahmer, Rachel Ward 

Publication date: 15 August 2022

Published in: Sampling Theory, Signal Processing, and Data Analysis (Search for Journal in Brave)

Abstract: We provide moment bounds for expressions of the type $(X^{(1)}otimesdotsotimes{X}^{(d)}{)}^{T}A(X^{(1)}otimesdotsotimes{X}^{(d)})$ where $otimes$ denotes the Kronecker product and $X^{(1)},dots,X^{(d)}$ are random vectors with independent, mean 0, variance 1, subgaussian entries. The bounds are tight up to constants depending on $d$ 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 $|B(X^{(1)}otimesdotsotimes{X}^{(d)}){|}_2$.

Full work available at URL: https://arxiv.org/abs/2106.13345

Recommendations

• Concentration inequalities for random tensors
• Hanson-Wright inequality and sub-Gaussian concentration
• Hanson-Wright inequality in Banach spaces
• A note on the Hanson-Wright inequality for random vectors with dependencies
• Sparse Hanson-Wright inequalities for subgaussian quadratic forms

zbMATH Keywords

Kronecker productrandom tensorsJohnson-Lindenstrauss embeddingsHanson-Wright inequalitysubgaussian random variables

Mathematics Subject Classification ID

Multilinear algebra, tensor calculus (15A69) Random matrices (probabilistic aspects) (60B20) Inequalities; stochastic orderings (60E15)

Cites Work

• Title not available (Why is that?)
• High-dimensional probability. An introduction with applications in data science
• Hanson-Wright inequality and sub-Gaussian concentration
• Invertibility of ``large submatrices with applications to the geometry of Banach spaces and harmonic analysis
• A mathematical introduction to compressive sensing
• A Bound on Tail Probabilities for Quadratic Forms in Independent Random Variables
• Moment inequalities for functions of independent random variables
• Decoupling inequalities for the tail probabilities of multivariate \(U\)- statistics
• New and Improved Johnson–Lindenstrauss Embeddings via the Restricted Isometry Property
• Decoupling inequalities for polynomial chaos
• Decoupling and Khintchine's inequalities for \(U\)-statistics
• Tail and moment estimates for chaoses generated by symmetric random variables with logarithmically concave tails
• Two-sided moment estimates for a class of nonnegative chaoses
• Estimates of moments and tails of Gaussian chaoses
• Moment estimates for chaoses generated by symmetric random variables with logarithmically convex tails
• A Practical Randomized CP Tensor Decomposition
• On decoupling, series expansions, and tail behavior of chaos processes
• Concentration inequalities for non-Lipschitz functions with bounded derivatives of higher order
• Moments of Gaussian chaoses in Banach spaces
• Decoupling inequalities for multilinear forms in independent symmetric random variables
• Concentration inequalities for polynomials in \(\alpha\)-sub-exponential random variables
• Concentration inequalities for random tensors
• Tail and moment estimates for a class of random chaoses of order two
• Optimal fast Johnson-Lindenstrauss embeddings for large data sets
• Faster Johnson-Lindenstrauss transforms via Kronecker products
• Oblivious Sketching of High-Degree Polynomial Kernels

Cited In (11)

• Some notes on concentration for \(\alpha\)-subexponential random variables
• Convenient tail bounds for sums of random tensors
• Moments tensors, Hilbert's identity, and \(k\)-wise uncorrelated random variables
• Probabilistic estimates for tensor products of random vectors
• A note on the Hanson-Wright inequality for random vectors with dependencies
• Tensor Bernstein concentration inequalities with an application to sample estimators for high-order moments
• Concentration inequalities for random tensors
• Johnson–Lindenstrauss Embeddings with Kronecker Structure
• Applied harmonic analysis and data science. Abstracts from the workshop held April 21--26, 2024
• Title not available (Why is that?)
• T-product tensors. II: Tail bounds for sums of random T-product tensors

This page was built for publication: The Hanson-Wright inequality for random tensors

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2164658)