低多重线性秩张量逼近的随机矩阵方法
A Random Matrix Approach to Low-Multilinear-Rank Tensor Approximation
AI总结:
该研究利用大随机矩阵理论分析尖峰张量模型的谱特性,预测截断MLSVD的重构性能,进而给出HOOI收敛的充分条件,证明大维极限下其收敛迭代次数趋于1,为低多重线性秩张量估计提供理论支撑。
摘要:
本工作对计算阈值附近的一般尖峰张量模型中植入低秩信号的估计问题提供了全面理解。依托大随机矩阵理论的标准工具,我们刻画了数据张量展开矩阵的大维谱行为,并给出了决定信号主方向可检测性的相关信噪比。这些结果能够准确预测截断多重线性SVD(MLSVD,多重线性奇异值分解)在非平凡区域的重构性能。这一点尤为重要,因为该方法是高阶正交迭代(HOOI)方案的初始化步骤,而HOOI收敛到最优低多重线性秩逼近的效果完全依赖于其初始化。我们给出了HOOI收敛的充分条件,并证明在大维极限下,收敛前的迭代次数趋于1。
英文摘要:
This work presents a comprehensive understanding of the estimation of a planted low-rank signal from a general spiked tensor model near the computational threshold. Relying on standard tools from the theory of large random matrices, we characterize the large-dimensional spectral behavior of the unfoldings of the data tensor and exhibit relevant signal-to-noise ratios governing the detectability of the principal directions of the signal. These results allow to accurately predict the reconstruction performance of truncated multilinear SVD (MLSVD) in the non-trivial regime. This is particularly important since it serves as an initialization of the higher-order orthogonal iteration (HOOI) scheme, whose convergence to the best low-multilinear-rank approximation depends entirely on its initialization. We give a sufficient condition for the convergence of HOOI and show that the number of iterations before convergence tends to $1$ in the large-dimensional limit.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。