We consider the problem of exactly fitting an ellipsoid (centered at ) to standard Gaussian random vectors in , as with . This problem is conjectured to undergo a sharp transition: with high probability, has a solution if , while has no solutions if . So far, only a trivial bound is known to imply the absence of solutions, while the sharpest results on the positive side assume (for a small constant) to prove that is solvable. In this work we study universality between this problem and a so-called "Gaussian equivalent", for which the same transition can be rigorously analyzed. Our main results are twofold. On the positive side, we prove that if , there exist an ellipsoid fitting all the points up to a small error, and that the lengths of its principal axes are bounded above and below. On the other hand, for , we show that achieving small fitting error is not possible if the length of the ellipsoid's shortest axis does not approach as (and in particular there does not exist any ellipsoid fit whose shortest axis length is bounded away from as ). To the best of our knowledge, our work is the first rigorous result characterizing the expected phase transition in ellipsoid fitting at . In a companion non-rigorous work, the first author and D. Kunisky give a general analysis of ellipsoid fitting using the replica method of statistical physics, which inspired the present work.
View on arXiv