Probabilistic classifiers with a generalized Gaussian scale mixture prior

Liu, Guoqing and Wu, Jianxin and Zhou, Suiping (2013) Probabilistic classifiers with a generalized Gaussian scale mixture prior. Pattern Recognition, 46 (1). pp. 332-345. ISSN 0031-3203

Full text is not in this repository.

This item is available in: Library Catalogue

Abstract

Most of the existing probabilistic classifiers are based on sparsity-inducing modeling. However, we show that sparsity is not always desirable in practice, and only an appropriate degree of sparsity is profitable. In this work, we propose a flexible probabilistic model using a generalized Gaussian scale mixture (GGSM) prior that can provide an appropriate degree of sparsity for its model parameters, and yield either sparse or non-sparse estimates according to the intrinsic sparsity of features in a dataset. Model learning is carried out by an efficient modified maximum a posterior (MAP) estimate. We also show relationships of the proposed model to existing probabilistic classifiers as well as iteratively re-weighted l1 and l2 minimizations. We then study different types of likelihood working with the GGSM prior in kernel-based setup, based on which an improved kernel-based GGIG is presented. Experiments demonstrate that the proposed method has better or comparable performances in linear classifiers as well as in kernel-based classification.

Item Type: Article
Keywords (uncontrolled): Classification; Prior distribution; Generalized Gaussian scale mixture; Likelihood function
Research Areas: A. > School of Science and Technology > Computer Science
Item ID: 12732
Useful Links:
Depositing User: Users 3197 not found.
Date Deposited: 22 Nov 2013 12:20
Last Modified: 13 Oct 2016 14:29
URI: http://eprints.mdx.ac.uk/id/eprint/12732

Actions (login required)

Edit Item Edit Item