Handling Sparsity via the Horseshoe
نویسندگان
چکیده
This paper presents a general, fully Bayesian framework for sparse supervised-learning problems based on the horseshoe prior. The horseshoe prior is a member of the family of multivariate scale mixtures of normals, and is therefore closely related to widely used approaches for sparse Bayesian learning, including, among others, Laplacian priors (e.g. the LASSO) and Student-t priors (e.g. the relevance vector machine). The advantages of the horseshoe are its robustness at handling unknown sparsity and large outlying signals. These properties are justified theoretically via a representation theorem and accompanied by comprehensive empirical experiments that compare its performance to benchmark alternatives.
منابع مشابه
The Horseshoe Estimator for Sparse Signals
This paper proposes a new approach to sparse-signal detection called the horseshoe estimator. We show that the horseshoe is a close cousin of the lasso in that it arises from the same class of multivariate scale mixtures of normals, but that it is almost universally superior to the double-exponential prior at handling sparsity. A theoretical framework is proposed for understanding why the horse...
متن کاملA NOVEL FUZZY-BASED SIMILARITY MEASURE FOR COLLABORATIVE FILTERING TO ALLEVIATE THE SPARSITY PROBLEM
Memory-based collaborative filtering is the most popular approach to build recommender systems. Despite its success in many applications, it still suffers from several major limitations, including data sparsity. Sparse data affect the quality of the user similarity measurement and consequently the quality of the recommender system. In this paper, we propose a novel user similarity measure based...
متن کاملHow many needles in the haystack? Adaptive inference and uncertainty quantification for the horseshoe
Abstract: We investigate the frequentist properties of Bayesian procedures for estimation and uncertainty quantification based on the horseshoe prior. We consider the sparse multivariate mean model and consider both the hierarchical Bayes method of putting a prior on the unknown sparsity level and the empirical Bayes method with the sparsity level estimated by maximum marginal likelihood. We sh...
متن کاملMortality in female horseshoe crabs (Limulus polyphemus) from biomedical bleeding and handling: implications for fisheries management
To cite this Article Leschen, A. S. andCorreia, S. J.(2010) 'Mortality in female horseshoe crabs (Limulus polyphemus) from biomedical bleeding and handling: implications for fisheries management', Marine and Freshwater Behaviour and Physiology, 43: 2, 135 — 147, First published on: 29 April 2010 (iFirst) To link to this Article: DOI: 10.1080/10236241003786873 URL: http://dx.doi.org/10.1080/1023...
متن کاملSparse Estimation with Generalized Beta Mixture and the Horseshoe Prior
In this paper, the use of the Generalized Beta Mixture (GBM) and Horseshoe distributions as priors in the Bayesian Compressive Sensing framework is proposed. The distributions are considered in a two-layer hierarchical model, making the corresponding inference problem amenable to Expectation Maximization (EM). We present an explicit, algebraic EM-update rule for the models, yielding two fast an...
متن کامل