Title
Exploration of the Use of a Self-Tuning Diffusion Map Framework
Speaker
David Friedenberg, Battelle Memorial Institute
Abstract
Diffusion maps are a powerful tool for identifying complicated structure and reducing dimensionality in a wide variety of applications. Representing the connectivity of a data set, diffusion maps project observations into a space in which standard methods can more easily model the structure. We explore the use of a flexible self-tuning diffusion map framework that incorporates local tuning parameters to capture group structure of varying density if present. We demonstrate the flexibility of the framework for a variety of applications, including document clustering, general clustering, classification and regression.
This work is joint with Dr. Rebecca Nugent from the Carnegie Mellon University Department of Statistics.