We describe an interesting application of the principle of local learning to density estimation. Locally weighted fitting of a Gaussian with a regularized full covariance matrix yields a density estimator which displays improved behavior in the case where much of the probability mass is...

The application of this work is to decision taking with financial time-series, using learning algorithms. The traditional approach is to train a model using a prediction criterion, such as minimizing the squared error between predictions and actual values of a dependent variable, or maximizing...

In this paper, we study and put under a common framework a number of non-linear dimensionality reduction methods, such as Locally Linear Embedding, Isomap, Laplacian Eigenmaps and kernel PCA, which are based on performing an eigen-decomposition (hence the name 'spectral'). That framework also...

In this paper I compare different models, a linear and a non-linear one, for forecasting industrial production by means of some related indicators. I claim that the difficulties associated with the correct identification of a non-linear model could be a possible cause of the often observed worse...

The use of linear parametric models for forecasting economic time series is widespread among practitioners, in spite of the fact that there is a large evidence of the presence of non-linearities in many of such time series. However, the empirical results stemming from the use of non-linear...

This paper revisits the issue of environment and development raised in the 1992 World Development Report, with new analysis tools and data. The paper discusses inference and interpretation in a machine learning framework. The results suggest that production gradually favors conserving the...