English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Statistical inference with the Elliptical Gamma Distribution

Hosseini, R., Sra, S., Theis, L., & Bethge, M. (2016). Statistical inference with the Elliptical Gamma Distribution. Computational Statistics & Data Analysis, 101, 29-43.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/11858/00-001M-0000-0027-7FC9-2 Version Permalink: http://hdl.handle.net/21.11116/0000-0000-FDD3-5
Genre: Journal Article

Files

show Files

Locators

show

Creators

show
hide
 Creators:
Hosseini, R, Author              
Sra, S, Author              
Theis, L1, Author              
Bethge, M1, Author              
Affiliations:
1Werner Reichardt Centre for Integrative Neuroscience, Tübingen, Germany, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: This paper studies mixture modeling using the Elliptical Gamma distribution (EGD)---a distribution that has parametrized tail and peak behaviors and offers richer modeling power than the multivariate Gaussian. First, we study maximum likelihood (ML) parameter estimation for a single EGD, a task that involves nontrivial conic optimization problems. We solve these problems by developing globally convergent fixed-point methods for them. Next, we consider fitting mixtures of EGDs, for which we first derive a closed-form expression for the KL-divergence between two EGDs and then use it in a ''split-and-merge'' expectation maximization algorithm. We demonstrate the ability of our proposed mixture modelling in modelling natural image patches.

Details

show
hide
Language(s):
 Dates: 2016-09
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: BibTex Citekey: HosseiniSTB2014
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: Computational Statistics & Data Analysis
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 101 Sequence Number: - Start / End Page: 29 - 43 Identifier: DOI: 10.1016/j.csda.2016.02.009