Soft Dimension Reduction for ICA by Joint Diagonalization on the Stiefel Manifold
نویسندگان
چکیده
Joint diagonalization for ICA is often performed on the orthogonal group after a pre-whitening step. Here we assume that we only want to extract a few sources after pre-whitening, and hence work on the Stiefel manifold of p-frames in R. The resulting method does not only use second-order statistics to estimate the dimension reduction and is therefore denoted as soft dimension reduction. We employ a trustregion method for minimizing the cost function on the Stiefel manifold. Applications to a toy example and functional MRI data show a higher numerical efficiency, especially when p is much smaller than n, and more robust performance in the presence of strong noise than methods based on pre-whitening.
منابع مشابه
A Matrix Joint Diagonalization Approach for Complex Independent Vector Analysis
Independent Vector Analysis (IVA) is a special form of Independent Component Analysis (ICA) in terms of group signals. Most IVA algorithms are developed via optimizing certain contrast functions. The main difficulty of these contrast function based approaches lies in estimating the unknown distribution of sources. On the other hand, tensorial approaches are efficient and richly available to the...
متن کاملA completed adaptive de-mixing algorithm on Stiefel manifold for ICA
Based on the one-bit-matching principle and by turning the de-mixing matrix into an orthogonal matrix via certain normalization, Ma et al proposed a one-bit-matching learning algorithm on the Stiefel manifold for independent component analysis [8]. But this algorithm is not adaptive. In this paper, an algorithm which can extract kurtosis and its sign of each independent source component directl...
متن کاملRiemannian Optimization Method on the Flag Manifold for Independent Subspace Analysis
Recent authors have investigated the use of manifolds and Lie group methods for independent component analysis (ICA), including the Stiefel and the Grassmann manifolds and the orthogonal group O(n). In this paper we introduce a new class of manifold, the generalized flag manifold, which is suitable for independent subspace analysis. The generalized flag manifold is a set of subspaces which are ...
متن کاملGeodesic Learning Algorithms Over Flag Manifolds
Recently manifold structures have attracted attentions in two folds in the machine learning literature. One is in the manifold learning problem, that is learning the intrinsic manifold structure in high dimensional datasets. Another is in the information geometric approach to learning – exploiting the geometry of the parameter space of learning machines such as neural networks for improving con...
متن کاملبهبود مدل تفکیککننده منیفلدهای غیرخطی بهمنظور بازشناسی چهره با یک تصویر از هر فرد
Manifold learning is a dimension reduction method for extracting nonlinear structures of high-dimensional data. Many methods have been introduced for this purpose. Most of these methods usually extract a global manifold for data. However, in many real-world problems, there is not only one global manifold, but also additional information about the objects is shared by a large number of manifolds...
متن کامل