Deterministic Conditions for Subspace Identifiability from Incomplete Sampling
Consider a generic $r$-dimensional subspace of $\mathbb{R}^d$, $r<d$, and suppose that we are only given projections of this subspace onto small subsets of the canonical coordinates. The paper establishes necessary and sufficient deterministic conditions on the subsets for subspace identifiability.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
To lie or not to lie in a subspace
Give deterministic necessary and sufficient conditions to guarantee that if a subspace fits certain partially observed data from a union of subspaces, it is because such data really lies in a subspace. Furthermore, Giv…
Identifiability of Complete Dictionary Learning
Sparse component analysis (SCA), also known as complete dictionary learning, is the following problem: Given an input matrix $M$ and an integer $r$, find a dictionary $D$ with $r$ columns and a matrix $B$ with $k$-sparse…
Dictionary LearningA Characterization of Deterministic Sampling Patterns for Low-Rank Matrix Completion
Low-rank matrix completion (LRMC) problems arise in a wide variety of applications. Previous theory mainly provides conditions for completion under missing-at-random samplings. This paper studies deterministic conditions…
Low-Rank Matrix CompletionMatrix CompletionMixed-Features Vectors and Subspace Splitting
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,…
ClusteringDictionary LearningRecommendation SystemsA Theoretical Analysis of Noisy Sparse Subspace Clustering on Dimensionality-Reduced Data
Subspace clustering is the problem of partitioning unlabeled data points into a number of clusters so that data points within one cluster lie approximately on a low-dimensional linear subspace. In many practical scenario…
ClusteringDimensionality Reduction