62 citations · 615 across the 49 of their papers we have counts for
20 papers · 1 filter
Independent vector analysis -- an introduction for statisticians
Miro Arvila, Klaus Nordhausen, Mika Sipilä +1
Blind source separation (BSS), particularly independent component analysis (ICA), has been widely used in various fields of science such as biomedical signal processing to recover…
Modelling multivariate spatio-temporal data with identifiable variational autoencoders
Mika Sipilä, Claudia Cappello, Sandra De Iaco +2
Modelling multivariate spatio-temporal data with complex dependency structures is a challenging task but can be simplified by assuming that the original variables are generated fro…
Invariant Coordinate Selection and Fisher discriminant subspace beyond the case of two groups
Colombe Becquart, Aurore Archimbaud, Anne Ruiz-Gazen +2
Invariant Coordinate Selection (ICS) is a multivariate technique that relies on the simultaneous diagonalization of two scatter matrices. It serves various purposes, including its…
Nonlinear blind source separation exploiting spatial nonstationarity
Mika Sipilä, Klaus Nordhausen, Sara Taskinen
In spatial blind source separation the observed multivariate random fields are assumed to be mixtures of latent spatially dependent random fields. The objective is to recover laten…
Robust and Resistant Regularized Covariance Matrices
David E. Tyler, Mengxi Yi, Klaus Nordhausen
We introduce a class of regularized M-estimators of multivariate scatter and show, analogous to the popular spatial sign covariance matrix (SSCM), that they possess high breakdown…
Tandem clustering with invariant coordinate selection
Andreas Alfons, Aurore Archimbaud, Klaus Nordhausen +1
For multivariate data, tandem clustering is a well-known technique aiming to improve cluster identification through initial dimension reduction. Nevertheless, the usual approach us…
Order Determination for Tensor-valued Observations Using Data Augmentation
Una Radojicic, Niko Lietzen, Klaus Nordhausen +1
Tensor-valued data benefits greatly from dimension reduction as the reduction in size is exponential in the number of modes. To achieve maximal reduction without loss in informatio…
Spatial Blind Source Separation in the Presence of a Drift
Christoph Muehlmann, Peter Filzmoser, Klaus Nordhausen
Multivariate measurements taken at different spatial locations occur frequently in practice. Proper analysis of such data needs to consider not only dependencies on-sight but also…
Blind source separation for non-stationary random fields
Christoph Muehlmann, François Bachoc, Klaus Nordhausen
Regional data analysis is concerned with the analysis and modeling of measurements that are spatially separated by specifically accounting for typical features of such data. Namely…
Stationary subspace analysis based on second-order statistics
Lea Flumian, Markus Matilainen, Klaus Nordhausen +1
In stationary subspace analysis (SSA) one assumes that the observable p-variate time series is a linear mixture of a k-variate nonstationary time series and a (p-k)-variate station…
Non-Gaussian component analysis: testing the dimension of the signal subspace
Una Radojicic, Klaus Nordhausen
Dimension reduction is a common strategy in multivariate data analysis which seeks a subspace which contains all interesting features needed for the subsequent analysis. Non-Gaussi…
Sliced Inverse Regression for Spatial Data
Christoph Muehlmann, Hannu Oja, Klaus Nordhausen
Sliced inverse regression is one of the most popular sufficient dimension reduction methods. Originally, it was designed for independent and identically distributed data and recent…
Independent Component Analysis for Compositional Data
Christoph Muehlmann, Kamila Fačevicová, Alžběta Gardlo +2
Compositional data represent a specific family of multivariate data, where the information of interest is contained in the ratios between parts rather than in absolute values of si…
Sliced Average Variance Estimation for Multivariate Time Series
Markus Matilainen, Christophe Croux, Klaus Nordhausen +1
Supervised dimension reduction for time series is challenging as there may be temporal dependence between the response and the predictors . Recently a time serie…
On the number of signals in multivariate time series
Markus Matilainen, Klaus Nordhausen, Joni Virta
We assume a second-order source separation model where the observed multivariate time series is a linear mixture of latent, temporally uncorrelated time series with some components…
ICS for Multivariate Outlier Detection with Application to Quality Control
Aurore Archimbaud, Klaus Nordhausen, Anne Ruiz-Gazen
In high reliability standards fields such as automotive, avionics or aerospace, the detection of anomalies is crucial. An efficient methodology for automatically detecting multivar…
Asymptotic and bootstrap tests for subspace dimension
Klaus Nordhausen, Hannu Oja, David E. Tyler
Most linear dimension reduction methods proposed in the literature can be formulated using an appropriate pair of scatter matrices, see e.g. Ye and Weiss (2003), Tyler et al. (2009…
A cautionary note on robust covariance plug-in methods
Klaus Nordhausen, David E. Tyler
Many multivariate statistical methods rely heavily on the sample covariance matrix. It is well known though that the sample covariance matrix is highly non-robust. One popular alte…
On asymptotics of ICA estimators and their performance indices
Pauliina Ilmonen, Klaus Nordhausen, Hannu Oja +1
Independent component analysis (ICA) has become a popular multivariate analysis and signal processing technique with diverse applications. This paper is targeted at discussing theo…
Averaging orthogonal projectors
Eero Liski, Klaus Nordhausen, Hannu Oja +1
Dimensionality is a major concern in analyzing large data sets. Some well known dimension reduction methods are for example principal component analysis (PCA), invariant coordinate…