33
7

Fitting an ellipsoid to a quadratic number of random points

Abstract

We consider the problem (P)(\mathrm{P}) of fitting nn standard Gaussian random vectors in Rd\mathbb{R}^d to the boundary of a centered ellipsoid, as n,dn, d \to \infty. This problem is conjectured to have a sharp feasibility transition: for any ε>0\varepsilon > 0, if n(1ε)d2/4n \leq (1 - \varepsilon) d^2 / 4 then (P)(\mathrm{P}) has a solution with high probability, while (P)(\mathrm{P}) has no solutions with high probability if n(1+ε)d2/4n \geq (1 + \varepsilon) d^2 /4. So far, only a trivial bound nd2/2n \geq d^2 / 2 is known on the negative side, while the best results on the positive side assume nd2/polylog(d)n \leq d^2 / \mathrm{polylog}(d). In this work, we improve over previous approaches using a key result of Bartl & Mendelson on the concentration of Gram matrices of random vectors under mild assumptions on their tail behavior. This allows us to give a simple proof that (P)(\mathrm{P}) is feasible with high probability when nd2/Cn \leq d^2 / C, for a (possibly large) constant C>0C > 0.

View on arXiv
Comments on this paper

We use cookies and other tracking technologies to improve your browsing experience on our website, to show you personalized content and targeted ads, to analyze our website traffic, and to understand where our visitors are coming from. See our policy.