Gradient based block coordinate descent algorithms for joint approximate diagonalization of matrices.
Jianze LiKonstantin UsevichPierre ComonPublished in: CoRR (2020)
Keyphrases
- data structure
- optimization problems
- learning algorithm
- exact and approximate
- linear algebra
- computational cost
- computationally intensive
- computationally efficient
- benchmark datasets
- genetic algorithm
- face recognition
- significant improvement
- theoretical analysis
- machine learning algorithms
- matrix multiplication
- neural network
- times faster
- worst case
- evolutionary algorithm
- reinforcement learning
- social networks