Deterministic Tensor Completion with Hypergraph Expanders
SIAM JOURNAL ON MATHEMATICS OF DATA SCIENCE(2021)
摘要
We provide a novel analysis of low-rank tensor completion based on hypergraith expanders. As a proxy for rank, we minimize the max-quasinorm of the tensor, which generalizes the max-norm for matrices. Our analysis is deterministic and shows that the number of samples required to approximately recover an order-t tensor with at most n entries per dimension is linear in n, under the assumption that the rank and order of the tensor are O(1). As steps in our proof, we find a new expander mixing lemma for a t-partite, t-uniform regular hypergraph model and prove several new properties about the tensor max-quasinorm. To the best of our knowledge, this is the first deterministic analysis of tensor completion. We develop a practical algorithm that solves a relaxed version of the max-quasinorm minimization problem, and we demonstrate its efficacy with numerical experiments.
更多查看译文
关键词
hypergraph, expander, tensor completion, linear algebra
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络