AI RESEARCH
Mild Over-Parameterization Benefits Asymmetric Tensor PCA
arXiv CS.LG
•
ArXi:2604.10208v1 Announce Type: new Asymmetric Tensor PCA (ATPCA) is a prototypical model for studying the trade-offs between sample complexity, computation, and memory. Existing algorithms for this problem typically require at least $d^{\left\lceil\overline{k}/2\right\rceil}$ state memory cost to recover the signal, where $d$ is the vector dimension and $\overline{k}$ is the tensor order.