Guaranteed Nonconvex Low-Rank Tensor Estimation via Scaled Gradient Descent
通过缩放梯度下降法保证非凸低秩张量估计
AI总结 本文提出ScaledGD算法，通过缩放梯度下降法在t-SVD框架下实现低秩张量估计的线性收敛，克服了传统方法在条件数依赖上的限制。
Comments This paper has been accepted for publication in the Journal of Machine Learning Research
