3 accepted papers
It has long been conjectured and empirically observed that neural networks tend to preserve clustering structure. This paper formalizes this conjecture. Specifically, we establish precise conditions for cluster structure preservation and derive bounds to quantify its extent. Through this analysis we…
Large amounts of missing data are becoming increasingly ubiquitous in modern high-dimensional datasets. Unfortunately, classical completion methods like low-rank, high-rank, or deep matrix completion (LRMC/HRMC/DMC) are often unable to handle real data that does not fall under their respective model…
Motivated by metagenomics, recommender systems, dictionary learning, and related problems, this paper introduces subspace splitting(SS): the task of clustering the entries of what we call amixed-features vector, that is, a vector whose subsets of coordinates agree with a collection of subspaces. We…