Independent Component Analysis via Energy-based and Kernel-based Mutual Dependence Measures
This work addresses ICA for signal processing and data analysis, offering an incremental improvement with better robustness to model misspecification.
The paper tackles the problem of independent component analysis (ICA) by generalizing an existing method to minimize mutual dependence measures, achieving competitive results when the model is correct and producing less dependent components than observed data when the model is misspecified, unlike other approaches that increase dependence.
We apply both distance-based (Jin and Matteson, 2017) and kernel-based (Pfister et al., 2016) mutual dependence measures to independent component analysis (ICA), and generalize dCovICA (Matteson and Tsay, 2017) to MDMICA, minimizing empirical dependence measures as an objective function in both deflation and parallel manners. Solving this minimization problem, we introduce Latin hypercube sampling (LHS) (McKay et al., 2000), and a global optimization method, Bayesian optimization (BO) (Mockus, 1994) to improve the initialization of the Newton-type local optimization method. The performance of MDMICA is evaluated in various simulation studies and an image data example. When the ICA model is correct, MDMICA achieves competitive results compared to existing approaches. When the ICA model is misspecified, the estimated independent components are less mutually dependent than the observed components using MDMICA, while they are prone to be even more mutually dependent than the observed components using other approaches.