A new convergence proof for the higher-order power method and generalizations
arXiv:1407.4586
Abstract
A proof for the point-wise convergence of the factors in the higher-order power method for tensors towards a critical point is given. It is obtained by applying established results from the theory of Łojasiewicz inequalities to the equivalent, unconstrained alternating least squares algorithm for best rank-one tensor approximation.
Cited by in corpus (11)
- Smooth PARAFAC Decomposition for Tensor Completion
- A Sharp Blockwise Tensor Perturbation Bound for Orthogonal Iteration
- Convergence of Alternating Least Squares Optimisation for Rank-One Approximation to High Order Tensors
- Fast algorithms for Higher-order Singular Value Decomposition from incomplete data
- On the convergence of higher-order orthogonality iteration
- Robust Eigenvectors of Symmetric Tensors
- Finding a low-rank basis in a matrix subspace
- Globally convergent Jacobi-type algorithms for simultaneous orthogonal symmetric tensor diagonalization
- On Convergence to Essential Singularities
- Tensor Canonical Correlation Analysis with Convergence and Statistical Guarantees
- Jacobi-type algorithms for homogeneous polynomial optimization on Stiefel manifolds with applications to tensor approximations