Convergence of Gradient-Based Block Coordinate Descent Algorithms for Nonorthogonal Joint Approximate Diagonalization of Matrices.
Jianze LiKonstantin UsevichPierre ComonPublished in: SIAM J. Matrix Anal. Appl. (2023)
Keyphrases
- learning algorithm
- orders of magnitude
- reinforcement learning
- significant improvement
- optimization problems
- computationally efficient
- theoretical analysis
- convergence rate
- optimization methods
- theoretical justification
- exact and approximate
- iterative algorithms
- linear algebra
- computationally intensive
- machine learning algorithms
- least squares
- computational complexity