Berry-Esseen bounds for random projections of $\ell_p^n$-balls
Samuel G. G. Johnston, Joscha Prochno

TL;DR
This paper establishes Berry-Esseen bounds for the convergence rate in the CLT for the Euclidean norm of random projections of vectors from high-dimensional ^n-balls, including randomized subspace dimensions and general -norms.
Contribution
It proves a Berry-Esseen theorem for random projections of ^n-balls under minimal conditions, confirming a conjecture and extending previous results to randomized settings.
Findings
Proved a Berry-Esseen bound for ^n-balls with diverging subspace dimension.
Confirmed the conjecture requiring only that the subspace dimension tends to infinity.
Analyzed the effect of randomizing the subspace dimension on CLT behavior.
Abstract
In this work we study the rate of convergence in the central limit theorem for the Euclidean norm of random orthogonal projections of vectors chosen at random from an -ball which has been obtained in [Alonso-Guti\'errez, Prochno, Th\"ale: Gaussian fluctuations for high-dimensional random projections of -balls, Bernoulli 25(4A), 2019, 3139--3174]. More precisely, for any let be a random subspace of dimension , the orthogonal projection onto , and be a random point in the unit ball of . We prove a Berry-Esseen theorem for under the condition that . This answers in the affirmative a conjecture of Alonso-Guti\'errez, Prochno, and Th\"ale who obtained a rate of convergence under the additional condition that as . In addition, we…
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
TopicsPoint processes and geometric inequalities · Geometry and complex manifolds · Geometric Analysis and Curvature Flows
