Uniform Convergence of Adaptive Graph-Based Regularization

Abstract. The regularization functional induced by the graph Laplacian of a random neighborhood graph based on the data is adaptive in two ways. First it adapts to an underlying manifold structure and second to the density of the data-generating probability measure. We identify in this paper the limit of the regularizer and show uniform convergence over the space of H

• Type: Conference
• Year: 2006
• Where: COLT
• Authors: Matthias Hein
• Keywords: COLT 2006, Graph Laplacian, H¨older Functions, Machine Learning, Random Neighborhood Graph