Proceedings of the 24th International Conference on Machine Learning 2007
DOI: 10.1145/1273496.1273639
|View full text |Cite
|
Sign up to set email alerts
|

Optimal dimensionality of metric space for classification

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
49
0

Year Published

2009
2009
2017
2017

Publication Types

Select...
4
2
1

Relationship

0
7

Authors

Journals

citations
Cited by 37 publications
(49 citation statements)
references
References 9 publications
0
49
0
Order By: Relevance
“…In [12], a metric space dimension reduction technique is proposed. The idea is to find a linear transform such that in the transformed space total within class distance is minimized, while total between class distance is maximized.…”
Section: Related Workmentioning
confidence: 99%
“…In [12], a metric space dimension reduction technique is proposed. The idea is to find a linear transform such that in the transformed space total within class distance is minimized, while total between class distance is maximized.…”
Section: Related Workmentioning
confidence: 99%
“…Yang et al [31] propose a Local Distance Metric (LDM) that addresses multimodal data distributions in distance metric learning by optimizing local compactness and local separability in a probabilistic framework. Finally, a number of recent studies [28], [32], [33], [34], [35], [38], [39], [40], [41], [42], [43], [44], [45], [46], [47], [48], [49] focus on examining and exploring the relationship among metric learning, dimensionality reduction, kernel learning, semi-supervised learning, and Bayesian learning.…”
Section: Related Workmentioning
confidence: 99%
“…Here, following the previous works in the supervised setting [11,1,2], the nearest neighbor algorithm is used for representing a simple classifier mentioned in the goal. Note that important special cases of SSL problems are transductive problems where we only want to predict the labels {y i } ℓ+u i=ℓ+1 of the given unlabeled examples.…”
Section: The Frameworkmentioning
confidence: 99%
“…The specification of "nearby examples" has been proven to be successful in discovering manifold and multi-modal structure [11,1,2,3,4,5,6,18,19,20,21,22]. See Figure 2 for explanations.…”
Section: Specification Of the Cost And Constraint Matricesmentioning
confidence: 99%
See 1 more Smart Citation