A Random Matrix Analysis of Symmetric Tensor Unfolding
arXiv:2611.05137v1 Announce Type: new Abstract: We study a fundamental problem in machine learning: partial recovery of a planted signal $\boldsymbol{v} \in \mathbb{S}^{n-1}$ from a spiked tensor $\boldsymbol{\mathsf{X}} = \lambda \, \boldsymbol{v}^{\otimes p} + \boldsymbol{\mathsf{Z}}$, where $\bo…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-11-04 05:00 · arXiv stat.ML
A Random Matrix Analysis of Symmetric Tensor Unfolding