Robust Optimization and Inference on Manifolds

Abstract

We propose a robust and scalable procedure for general optimization and inference problems on manifolds leveraging the classical idea of 'median-of-means' estimation. This is motivated by ubiquitous examples and applications in modern data science in which a statistical learning problem can be cast as an optimization problem over manifolds. Being able to incorporate the underlying geometry for inference while addressing the need for robustness and scalability presents great challenges. We address these challenges by first proving a key lemma that characterizes some crucial properties of geometric medians on manifolds. In turn, this allows us to prove robustness and tighter concentration of our proposed final estimator in a subsequent theorem. This estimator aggregates a collection of subset estimators by taking their geometric median over the manifold. We illustrate bounds on this estimator via calculations in explicit examples. The robustness and scalability of the procedure is illustrated in numerical examples on both simulated and real data sets.

Shape-Preserving Dimensionality Reduction : An Algorithm and Measures of Topological Equivalence

“…One practical issue is that computational cost in evaluating the cost function (1) grows exponentially as |X| → ∞, which makes the optimization for an optimal linear projection computationally intractable for a large dataset. Recently, a distributed learning framework was proposed for robust and scalable estimation of a manifold-valued estimator via geometric median (Lin et al;.…”