Random version of Dvoretzky's theorem in $\ell_p^n$
Grigoris Paouris, Petros Valettas, Joel Zinn

TL;DR
This paper investigates the critical dimension for random sections of the _p^n-ball to be nearly spherical, providing estimates that match known results at the extremes and analyzing _p-norm concentration.
Contribution
It offers new bounds on the critical dimension for _p^n-balls, extending understanding across all p and _epsilon, with tight concentration bounds for _p-norms.
Findings
Derived bounds for critical dimension k(n,p,_epsilon) for all p and _epsilon.
Matched estimates with known results at p=1 and p=_infinity.
Provided tight Gaussian concentration bounds for _p-norms.
Abstract
We study the dependence on in the critical dimension for which one can find random sections of the -ball which are -spherical. We give lower (and upper) estimates for for all eligible values and as , which agree with the sharp estimates for the extreme values and . Toward this end, we provide tight bounds for the Gaussian concentration of the -norm.
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.
