Corpus ID: 88514745

Global-Local Mixtures

  title={Global-Local Mixtures},
  author={Anindya Bhadra and J. Datta and N. Polson and Brandon T. Willard},
  journal={arXiv: Statistics Theory},
  • Anindya Bhadra, J. Datta, +1 author Brandon T. Willard
  • Published 2016
  • Mathematics
  • arXiv: Statistics Theory
  • Global-local mixtures are derived from the Cauchy-Schlomilch and Liouville integral transformation identities. We characterize well-known normal-scale mixture distributions including the Laplace or lasso, logit and quantile as well as new global-local mixtures. We also apply our methodology to convolutions that commonly arise in Bayesian inference. Finally, we conclude with a conjecture concerning bridge and uniform correlation mixtures. 

    Paper Mentions

    Horseshoe Regularization for Machine Learning in Complex and Deep Models.
    • 3
    • PDF
    Lasso Meets Horseshoe : A Survey.
    • 22
    • PDF
    Horseshoe Regularization for Feature Subset Selection
    • 7
    • PDF
    miniKanren as a Tool for Symbolic Computation in Python


    Publications referenced by this paper.
    Data augmentation for non-Gaussian regression models using variance-mean mixtures
    • 29
    • PDF
    Normal Variance-Mean Mixtures and z Distributions
    • 350
    • Highly Influential
    Normal scale mixtures and dual probability densities
    • 66
    Scale Mixtures of Normal Distributions
    • 578
    Default Bayesian Analysis with Global-Local Shrinkage Priors
    • 26
    • PDF
    On the half-cauchy prior for a global scale parameter
    • 236
    • PDF
    Probabilistic Applications of the Schlömilch Transformation
    • 21
    The Horseshoe+ Estimator of Ultra-Sparse Signals
    • 81
    • PDF