Operator Norm

14,000,000 Leading Edge Experts on the ideXlab platform

Scan Science and Technology

Contact Leading Edge Experts & Companies

Scan Science and Technology

Contact Leading Edge Experts & Companies

The Experts below are selected from a list of 27846 Experts worldwide ranked by ideXlab platform

Valentin A. Zagrebnov - One of the best experts on this subject based on the ideXlab platform.

V.a. Zagrebnov - One of the best experts on this subject based on the ideXlab platform.

Vincent Cachia - One of the best experts on this subject based on the ideXlab platform.

Hagen Neidhardt - One of the best experts on this subject based on the ideXlab platform.

Pierre Pudlo - One of the best experts on this subject based on the ideXlab platform.

  • Operator Norm Convergence of Spectral Clustering on Level Sets
    Journal of Machine Learning Research, 2010
    Co-Authors: Bruno Pelletier, Pierre Pudlo
    Abstract:

    Following Hartigan (1975), a cluster is defined as a connected component of the t-level set of the underlying density, that is, the set of points for which the density is greater than t. A clustering algorithm which combines a density estimate with spectral clustering techniques is proposed. Our algorithm is composed of two steps. First, a nonparametric density estimate is used to extract the data points for which the estimated density takes a value greater than t. Next, the extracted points are clustered based on the eigenvectors of a graph Laplacian matrix. Under mild assumptions, we prove the almost sure convergence in Operator Norm of the empirical graph Laplacian Operator associated with the algorithm. Furthermore, we give the typical behavior of the representation of the data set into the feature space, which establishes the strong consistency of our proposed algorithm.

  • Operator Norm convergence of spectral clustering on level sets
    arXiv: Machine Learning, 2010
    Co-Authors: Bruno Pelletier, Pierre Pudlo
    Abstract:

    Following Hartigan, a cluster is defined as a connected component of the t-level set of the underlying density, i.e., the set of points for which the density is greater than t. A clustering algorithm which combines a density estimate with spectral clustering techniques is proposed. Our algorithm is composed of two steps. First, a nonparametric density estimate is used to extract the data points for which the estimated density takes a value greater than t. Next, the extracted points are clustered based on the eigenvectors of a graph Laplacian matrix. Under mild assumptions, we prove the almost sure convergence in Operator Norm of the empirical graph Laplacian Operator associated with the algorithm. Furthermore, we give the typical behavior of the representation of the dataset into the feature space, which establishes the strong consistency of our proposed algorithm.