The hypothesis that high dimensional data tend to lie in the vicinity of a low dimensional manifold is the basis of manifold learning. The goal of this paper is to develop an algorithm (with accompanying complexity guarantees) for testing the existence of a manifold that fits a probability distribution supported in a separable Hilbert space, only using i.i.d. samples from that distribution. More precisely, our setting is the following. Suppose that data are drawn independently at random from a probability distribution
supported on the unit ball of a separable Hilbert space
. Let
be the set of submanifolds of the unit ball of
whose volume is at most
and reach (which is the supremum of all
such that any point at a distance less than
has a unique nearest point on the manifold) is at least
. Let
denote the mean-squared distance of a random point from the probability distribution
to
. We obtain an algorithm that tests the manifold hypothesis in the following sense. The algorithm takes i.i.d. random samples from
as input and determines which of the following two is true (at least one must be): There exists
such that
There exists no
such that
The answer is correct with probability at least
.