Part of Advances in Neural Information Processing Systems 14 (NIPS 2001)
Peter Meinicke, Helge Ritter
We suggest a nonparametric framework for unsupervised learning of projection models in terms of density estimation on quantized sample spaces. The objective is not to optimally reconstruct the data but in- stead the quantizer is chosen to optimally reconstruct the density of the data. For the resulting quantizing density estimator (QDE) we present a general method for parameter estimation and model selection. We show how projection sets which correspond to traditional unsupervised meth- ods like vector quantization or PCA appear in the new framework. For a principal component quantizer we present results on synthetic and real- world data, which show that the QDE can improve the generalization of the kernel density estimator although its estimate is based on significantly lower-dimensional projection indices of the data.