On the convergence of Jacobi-type algorithms for Independent Component Analysis
arXiv:1912.07194
Abstract
Jacobi-type algorithms for simultaneous approximate diagonalization of real (or complex) symmetric tensors have been widely used in independent component analysis (ICA) because of their good performance. One natural way of choosing the index pairs in Jacobi-type algorithms is the classical cyclic ordering, while the other way is based on the Riemannian gradient in each iteration. In this paper, we mainly review in an accessible manner our recent results in a series of papers about weak and global convergence of these Jacobi-type algorithms. These results are mainly based on the Lojasiewicz gradient inequality.
arXiv comment5 pages
References in corpus (5)
- Tensor Decomposition for Signal Processing and Machine Learning
- Tensor Decompositions for Signal Processing Applications From Two-way to Multiway Component Analysis
- Global rates of convergence for nonconvex optimization on manifolds
- Jacobi-type algorithm for low rank orthogonal approximation of symmetric tensors and its convergence analysis
- Hermitian Tensor Decompositions