Global Convergence of Triangularized Orthogonalization-free Method

Abstract

This paper proves the global convergence of a triangularized orthogonalization-free method (TriOFM). TriOFM, in general, applies a triangularization idea to the gradient of an objective function and removes the rotation invariance in minimizers. More precisely, in this paper, the TriOFM works as an eigensolver for sizeable sparse matrices and obtains eigenvectors without any orthogonalization step. Due to the triangularization, the iteration is a discrete-time flow in a non-conservative vector field. The global convergence relies on the stable manifold theorem, whereas the convergence to stationary points is proved in detail in this paper. We provide two proofs inspired by the noisy power method and the noisy optimization method, respectively.

References in corpus (4)

• No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis
• Exact Guarantees on the Absence of Spurious Local Minima for Non-negative Rank-1 Robust Principal Component Analysis
• Triangularized Orthogonalization-free Method for Solving Extreme Eigenvalue Problems
• On the global convergence of randomized coordinate gradient descent for non-convex optimization