A new metric on the manifold of kernel matrices with application to matrix geometric means

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

117 Scopus citations

Abstract

Symmetric positive definite (spd) matrices pervade numerous scientific disciplines, including machine learning and optimization. We consider the key task of measuring distances between two spd matrices; a task that is often nontrivial whenever the distance function must respect the non-Euclidean geometry of spd matrices. Typical non-Euclidean distance measures such as the Riemannian metric δR(X, Y) = ∥log(Y-1/2XY -1/2)∥F, are computationally demanding and also complicated to use. To allay some of these difficulties, we introduce a new metric on spd matrices, which not only respects non-Euclidean geometry but also offers faster computation than δR while being less complicated to use. We support our claims theoretically by listing a set of theorems that relate our metric to δR(X, Y), and experimentally by studying the nonconvex problem of computing matrix geometric means based on squared distances.

Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 25
Subtitle of host publication26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012
Pages144-152
Number of pages9
StatePublished - 2012
Externally publishedYes
Event26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012 - Lake Tahoe, NV, United States
Duration: 3 Dec 20126 Dec 2012

Publication series

NameAdvances in Neural Information Processing Systems
Volume1
ISSN (Print)1049-5258

Conference

Conference26th Annual Conference on Neural Information Processing Systems 2012, NIPS 2012
Country/TerritoryUnited States
CityLake Tahoe, NV
Period3/12/126/12/12

Fingerprint

Dive into the research topics of 'A new metric on the manifold of kernel matrices with application to matrix geometric means'. Together they form a unique fingerprint.

Cite this