The Feature Importance Ranking Measure (2009)
Zien, Alexander, Kraemer, Nicole, Sonnenburg, Soeren, Raetsch, Gunnar
Most accurate predictions are typically obtained by learning machines with complex feature spaces (as e.g. induced by kernels). Unfortunately, such decision rules are hardly accessible to humans and...
Kraemer, Nicole, Schaefer, Juliane, Boulesteix, Anne-Laure
Graphical Gaussian models are popular tools for the estimation of (undirected) gene association networks from microarray data. A key issue when the number of variables greatly exceeds the number of...
On the Peaking Phenomenon of the Lasso in Model Selection (2009)
I briefly report on some unexpected results that I obtained when optimizing the model parameters of the Lasso. In simulations with varying observations-to-variables ratio n=p, I typically observe a...
Kernel Conjugate Gradient is Universally Consistent (2009)
Blanchard, Gilles, Kraemer, Nicole
We study the statistical consistency of conjugate gradient applied to a bounded regression learning problem seen as an inverse problem defined in a reproducing kernel Hilbert space. This approach...
Lanczos Approximations for the Speedup of Kernel Partial Least Squares Regression (2009)
Kraemer, Nicole, Sugiyama, Masashi, Braun, Mikio
The runtime for Kernel Partial Least Squares (KPLS) to compute the fit is quadratic in the number of examples. However, the necessity of obtaining sensitivity measures as degrees of freedom for model...
Sparse Causal Discovery in Multivariate Time Series (2009)
Haufe, Stefan, Nolte, Guido, Mueller, Klaus-Robert, Kraemer, Nicole
Our goal is to estimate causal interactions in multivariate time series. Using vector autoregressive (VAR) models, these can be defined based on non-vanishing coefficients belonging to respective...
Penalized Partial Least Squares Based on B-Splines Transformations (2006)
Kraemer, Nicole, Boulesteix, Anne-Laure, Tutz, Gerhard
We propose a novel method to model nonlinear regression problems by adapting the principle of penalization to Partial Least Squares (PLS). Starting with a generalized additive model, we expand the...
Boosting for Functional Data (2006)
We deal with the task of supervised learning if the data is of functional type. The crucial point is the choice of the appropriate fitting method (learner). Boosting is a stepwise technique that...
On the shrinkage behavior of partial least squares regression (2005)
We present a formula for the shrinkage factors of the Partial Least Squares regression estimator and deduce some of their properties, in particular the known fact that some of the factors are >1. We...
Local models for ramified unitary groups (2003)
In this article, we study local models associated to certain Shimura varieties. In particular, we present a resoultion of their singularities. As a consequence, we are able to determine the...