Minimax adaptive estimation in manifold inference
share
We focus on the problem of manifold estimation: given a set of observations sampled close to some unknown submanifold M, one wants to recover information about the geometry of M. Minimax estimators which have been proposed so far all depend crucially on the a priori knowledge of some parameters quantifying the regularity of M (such as its reach), whereas those quantities will be unknown in practice. Our contribution to the matter is twofold: first, we introduce a one-parameter family of manifold estimators (M̂_t)_t≥ 0, and show that for some choice of t (depending on the regularity parameters), the corresponding estimator is minimax on the class of models of C^2 manifolds introduced in [Genovese et al., Manifold estimation and singular deconvolution under Hausdorff loss]. Second, we propose a completely data-driven selection procedure for the parameter t, leading to a minimax adaptive manifold estimator on this class of models. The same selection procedure is then used to design adaptive estimators for tangent spaces and homology groups of the manifold M.
READ FULL TEXT