Gauss–Southwell Type Descent Methods for Low-Rank Matrix Optimization
研究了用于低秩矩阵优化的梯度相关方法，比较了基于高斯-索斯韦尔型选择规则的两种搜索方向，发现基于黎曼梯度的版本对奇异值和条件数更鲁棒。
Abstract We consider gradient-related methods for low-rank matrix optimization with a smooth cost function. The methods operate on single factors of the low-rank factorization and share aspects of both alternating and Riemannian optimization. Two possible choices for the search directions based on Gauss–Southwell type selection rules are compared: one using the gradient of a factorized non-convex formulation, the other using the Riemannian gradient. While both methods provide gradient convergence guarantees that are similar to the unconstrained case, numerical experiments on a quadratic cost function indicate that the version based on the Riemannian gradient is significantly more robust with respect to small singular values and the condition number of the cost function. As a side result of our approach, we also obtain new convergence results for the alternating least squares method.