Probabilistic Recovery of Multiple Subspaces in Point Clouds by Geometric lp Minimization

We assume data independently sampled from a mixture distribution on the unit ball of the D-dimensional Euclidean space with K+1 components: the first component is a uniform distribution on that ball representing outliers and the other K components are uniform distributions along K d-dimensional linear subspaces restricted to that ball. We study both the simultaneous recovery of all K underlying subspaces and the recovery of the best l0 subspace (i.e., with largest number of points) by minimizing the lp-averaged distances of data points from d-dimensional subspaces of the D-dimensional space. Unlike other lp minimization problems, this minimization is non-convex for all p>0 and thus requires different methods for its analysis. We show that if 0<p <= 1, then both all underlying subspaces and the best l0 subspace can be precisely recovered by lp minimization with overwhelming probability. This result extends to additive homoscedastic uniform noise around the subspaces (i.e., uniform distribution in a strip around them) and near recovery with an error proportional to the noise level. On the other hand, if K>1 and p>1, then we show that both all underlying subspaces and the best l0 subspace cannot be recovered and even nearly recovered. Further relaxations are also discussed. We use the results of this paper for partially justifying recent effective algorithms for modeling data by mixtures of multiple subspaces as well as for discussing the effect of using variants of lp minimizations in RANSAC-type strategies for single subspace recovery.