Abstract | ||
---|---|---|
The recovery of the mixture of an N-dimensional signal generated by N independent processes is a well studied problem (see e.g. [1,10]) and robust algorithms that solve this problem by Joint Diagonalization exist. While there is a lot of empirical evidence suggesting that these algorithms are also capable of solving the case where the source signals have block structure (apart from a final permutation recovery step), this claim could not be shown yet - even more, it previously was not known if this model separable at all. We present a precise definition of the subspace model, introducing the notion of simple components, show that the decomposition into simple components is unique and present an algorithm handling the decomposition task. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1007/978-3-642-15995-4_46 | LVA/ICA |
Keywords | Field | DocType |
joint diagonalization,order subspace analysis,block structure,n independent process,final permutation recovery step,simple decomposition,model separable,subspace model,precise definition,decomposition task,simple component,empirical evidence,second order | Combinatorics,Irreducible component,Block structure,Subspace topology,Algebra,Permutation,Separable space,Blind signal separation,Mathematics | Conference |
Volume | ISSN | ISBN |
6365 | 0302-9743 | 3-642-15994-X |
Citations | PageRank | References |
5 | 0.50 | 7 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Harold W. Gutch | 1 | 45 | 4.60 |
Takanori Maehara | 2 | 10 | 0.99 |
Fabian J. Theis | 3 | 931 | 85.37 |