BriefGPT.xyz
Jul, 2012
张量恢复中增广迹范数模型的保证
Guarantees of Augmented Trace Norm Models in Tensor Recovery
HTML
PDF
Ziqiang Shi, Jiqing Han, Tieran Zheng, Shiwen Deng, Ji Li
TL;DR
本文研究了低秩张量的恢复保证,其中使用了迹范数和Frobenius范数来最小化张量,得到了与最小化迹范数类似的精确保证,只要满足感知算子的鸟巢空间性质,受限等谱性质或球面截面性质。
Abstract
This paper studies the
recovery guarantees
of the models of minimizing $\|\mathcal{X}\|_*+\frac{1}{2\alpha}\|\mathcal{X}\|_F^2$ where $\mathcal{X}$ is a tensor and $\|\mathcal{X}\|_*$ and $\|\mathcal{X}\|_F$ are the trace and
→