Nonparametric independent component analysis

Nonparametric Independent Component Analysis

​Rank based Least-squares Independent Component Analysis

  In this paper, we propose a nonparametric rank-based alternative to the least-squares independent component analysis algorithm developed. The basic idea is to estimate the squared-loss mutual information, which used as the objective function of the algorithm, based on its copula density version. Therefore, no marginal densities have to be estimated. We provide empirical evaluation of th...

Newton-Like Methods for Nonparametric Independent Component Analysis

The performance of ICA algorithms significantly depends on the choice of the contrast function and the optimisation algorithm used in obtaining the demixing matrix. In this paper we focus on the standard linear nonparametric ICA problem from an optimisation point of view. It is well known that after a pre-whitening process, the problem can be solved via an optimisation approach on a suitable ma...

Independent Component Analysis via Nonparametric Maximum Likelihood Estimation By

Independent Component Analysis (ICA) models are very popular semiparametric models in which we observe independent copies of a random vector X =AS, where A is a non-singular matrix and S has independent components. We propose a new way of estimating the unmixing matrix W = A−1 and the marginal distributions of the components of S using nonparametric maximum likelihood. Specifically, we study th...

Nonparametric mixture models with conditionally independent multivariate component densities

Models and algorithms for nonparametric estimation of finite multivariate mixtures have been recently proposed, where it is usually assumed that coordinates are independent conditional on the subpopulation from which each observation is drawn. Hence in these models the dependence structure comes only from the mixture. This assumption is relaxed, allowing for independent multivariate blocks of c...