Главная

Antony Joseph

  1. Gaussian Rate-Distortion via Sparse Regression over Compact Dictionaries.

    Втр, 02/07/2012 - 15:01 — SomNambul
    Authors: Sekhar Tatikonda, Antony Joseph, Ramji Venkataramanan
    Subjects: Information Theory
    Abstract

    We study a class of codes for compressing memoryless Gaussian sources,
    designed using the statistical framework of high-dimensional linear regression.
    Codewords are linear combinations of subsets of columns of a design matrix.
    With maximum-likelihood encoding we show that such a codebook can attain the
    rate-distortion function with the optimal error-exponent, for all distortions
    below a specified value. The structure of the codebook is motivated by an
    analogous construction proposed recently by Barron and Joseph for communication
    over an AWGN channel.

  2. Variable Selection in High Dimensions with Random Designs and Orthogonal Matching Pursuit.

    Втр, 09/06/2011 - 15:01 — SomNambul
    Authors: Antony Joseph
    Subjects: Machine Learning
    Abstract

    The performance of Orthogonal Matching Pursuit (OMP) for variable selection
    is analyzed for random designs. When contrasted with the deterministic case,
    since the performance is here measured after averaging over the distribution of
    the design matrix, one can have far less stringent sparsity constraints on the
    coefficient vector. We demonstrate that for exact sparse vectors, the
    performance of the OMP is similar to known results on the Lasso algorithm
    [\textit{IEEE Trans. Inform. Theory} \textbf{55} (2009) 2183--2202].

  3. Toward Fast Reliable Communication at Rates Near Capacity with Gaussian Noise.

    Втр, 06/22/2010 - 15:01 — SomNambul
    Authors: Antony Joseph, Andrew R Barron
    Subjects: Information Theory
    Abstract

    For the additive Gaussian noise channel with average codeword power
    constraint, sparse superposition codes and adaptive successive decoding is
    developed. Codewords are linear combinations of subsets of vectors, with the
    message indexed by the choice of subset. A feasible decoding algorithm is
    presented. Communication is reliable with error probability exponentially small
    for all rates below the Shannon capacity.

  4. Least Squares Superposition Codes of Moderate Dictionary Size, Reliable at Rates up to Capacity.

    Пнд, 06/21/2010 - 15:01 — SomNambul
    Authors: Andrew R. Barron, Antony Joseph
    Subjects: Information Theory
    Abstract

    For the additive white Gaussian noise channel with average codeword power
    constraint, new coding methods are devised in which the codewords are sparse
    superpositions, that is, linear combinations of subsets of vectors from a given
    design, with the possible messages indexed by the choice of subset. Decoding is
    by least squares, tailored to the assumed form of linear combination.
    Communication is shown to be reliable with error probability exponentially
    small for all rates up to the Shannon capacity.

Math-arch

RSS-материал