CARE: Large Precision Matrix Estimation for Compositional Data

arXiv:2309.06985v2 Announce Type: replace-cross
Abstract: High-dimensional compositional data are prevalent in many applications. The simplex constraint poses intrinsic challenges to inferring the conditional dependence relationships among the components forming a composition, as encoded by a large precision matrix. We introduce a precise specification of the compositional precision matrix and relate it to its basis counterpart, which is shown to be asymptotically identifiable under suitable sparsity assumptions. By exploiting this connection, we propose a composition adaptive regularized estimation (CARE) method for …

abstract applications arxiv challenges components data intrinsic math.st matrix precision relationships stat.ap stat.me stat.ml stat.th type