Here, a separation theorem about Independent Subspace Analysis (ISA), a generalization of Independent Component Analysis (ICA) is proven. According to the theorem, ISA estimation can be executed in two steps under certain conditions. In the first step, 1-dimensional ICA estimation is executed. In the second step, optimal permutation of the ICA elements is searched for. We present sufficient conditions for the ISA Separation Theorem. Namely, we shall show that (i) elliptically symmetric sources, (ii) 2-dimensional sources invariant to 90 degree rotation, among others, satisfy the conditions of the theorem.

翻译：在这里,关于独立子空间分析(ISA)的分离理论得到了证明,独立组成部分分析(ICA)的概括性得到了证明。根据理论,ISA的估算可以在某些条件下分两个步骤进行。第一步,执行一维的ICA估计。在第二步,国际空间分析(ISA)各单元的最佳排列。我们为ISA的分离理论(ISA)提供了充分的条件。也就是说,我们将显示(一) 椭圆对称源,(二) 二维源,可旋转至90度,等等,符合该理论的条件。