A0243
Title: Hypothesis testing for high-dimensional tensor signals via tensor contraction
Authors: Zhenggang Wang - Southeast University (China) [presenting]
Abstract: Hypothesis testing problems are considered for low-rank and high-dimensional tensor signals. Hypothesis testing for tensor is generally challenging due to the high dimension and lack of meaningful test statistics. By exploiting a recent tensor contraction method, relevant test statistics are proposed and validated using eigenvalues of a data matrix resulting from the tensor contraction. The matrix has a long-range dependence among its entries, which makes the analysis of the matrix challenging, involved, and distinct from standard random matrix theory. The approach provides a novel framework for addressing hypothesis-testing problems in the context of high-dimensional tensor signals.
