English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
 Local TagsStatisticsRelease HistoryDetailsSummary
  Geometric optimisation on positive definite matrices with application to elliptically contoured distributions

Sra, S., & Hosseini, R. (2014). Geometric optimisation on positive definite matrices with application to elliptically contoured distributions. In C. Burges, L. Bottou, M. Welling, & Z. Ghahramani (Eds.), Advances in Neural Information Processing Systems 26 (pp. 2564-2572). Red Hook, NY, USA: Curran.

Item is

 

show all hide all

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0001-2D4F-6 Version Permalink: http://hdl.handle.net/21.11116/0000-0001-2D54-F
Genre: Conference Paper

Files

show Files

Creators

show
hide
 Creators:
Sra, Suvrit1, Author              
Hosseini, R, Author
Affiliations:
1Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1497647              

Content

show
hide
Free keywords: -
 Abstract: Hermitian positive definite (hpd) matrices recur throughout machine learning, statistics, and optimisation. This paper develops (conic) geometric optimisation on the cone of hpd matrices, which allows us to globally optimise a large class of nonconvex functions of hpd matrices. Specifically, we first use the Riemannian manifold structure of the hpd cone for studying functions that are nonconvex in the Euclidean sense but are geodesically convex (g-convex), hence globally optimisable. We then go beyond g-convexity, and exploit the conic geometry of hpd matrices to identify another class of functions that remain amenable to global optimisation without requiring g-convexity. We present key results that help recognise g-convexity and also the additional structure alluded to above. We illustrate our ideas by applying them to likelihood maximisation for a broad family of elliptically contoured distributions: for this maximisation, we derive novel, parameter free fixed-point algorithms. To our knowledge, ours are the most general results on geometric optimisation of hpd matrices known so far. Experiments show that advantages of using our fixed-point algorithms.

Details

show
hide
Language(s):
 Dates: 2013-122014
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: -
 Degree: -

Event

show
hide
Title: Twenty-Seventh Annual Conference on Neural Information Processing Systems (NIPS 2013)
Place of Event: Stateline, NV, USA
Start-/End Date: -

Legal Case

show

Project information

show

Source 1

show
hide
Title: Advances in Neural Information Processing Systems 26
Source Genre: Proceedings
 Creator(s):
Burges, CJC, Editor
Bottou, L, Editor
Welling, M, Editor
Ghahramani, Z, Editor
Weinberger , KQ, Author
Affiliations:
-
Publ. Info: Red Hook, NY, USA : Curran
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 2564 - 2572 Identifier: ISBN: 978-1-63266-024-4