Learning distance functions using equivalence relations

Aharon Bar-Hillel; Tomer Hertz; Noam Shental; Daphna Weinshall

Abstract

We address the problem of learning distance metrics using side-information in the form of groups of &quot;similar&quot; points. We propose to use the RCA algorithm, which is a simple and e#cient algorithm for learning a full ranked Mahalanobis metric (Shental et al., 2002).

Keywords

Mahalanobis distanceMetric (unit)Cluster analysisMathematicsAlgorithmDistance matrixComputer scienceArtificial intelligence

Affiliated Institutions

Hebrew University of Jerusalem IL

Related Publications

A Split-Merge Markov chain Monte Carlo Procedure for the Dirichlet Process Mixture Model

Sonia Jain , Radford M. Neal

This article proposes a split-merge Markov chain algorithm to address the problem of inefficient sampling for conjugate Dirichlet process mixture models. Traditional Markov chai...

2004 Journal of Computational and Graphica... 464 citations

Learning Segmentation by Random Walks

Marina Meilă , Jianbo Shi

We present a new view of image segmentation by pairwise similarities. We interpret the similarities as edge ows in a Markov random walk and study the eigenvalues and eigenvector...

2000 370 citations

Publication Info

Year: 2003
Type: article
Pages: 11-18
Citations: 433
Access: Closed

External Links

Citation Metrics

433

OpenAlex

Cite This

APA Style

                            
                                    Aharon Bar-Hillel, 
                                
                                    Tomer Hertz, 
                                
                                    Noam Shental
                                
                                et al.
                            
                            (2003). 
                            Learning distance functions using equivalence relations. 
                            
                            , 11-18.