Large Margin Non-Linear Embedding

Zien, A; Candela, JQ

doi:10.1145/1102351.1102485

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Conference Paper

Large Margin Non-Linear Embedding

MPS-Authors

/persons/resource/persons84331

Zien, A
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;
Max Planck Institute for Biological Cybernetics, Max Planck Society;

/persons/resource/persons83845

Candela, JQ
Friedrich Miescher Laboratory, Max Planck Society;

External Resource

https://dl.acm.org/citation.cfm?doid=1102351.1102485
(Publisher version)

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

Fulltext (public)

pdf3375.pdf
(Any fulltext), 316KB

Supplementary Material (public)

There is no public supplementary material available

Citation

Zien, A., & Candela, J. (2005). Large Margin Non-Linear Embedding. In S. Dzeroski, L. de Raedt, & S. Wrobel (Eds.), ICML '05: 22nd international conference on Machine learning (pp. 1065-1072). New York, NY, USA: ACM Press.

Cite as: https://hdl.handle.net/11858/00-001M-0000-0013-D4B9-A

Abstract

It is common in classification methods to first place data in a vector
space and then learn decision boundaries. We propose reversing that
process: for fixed decision boundaries, we ``learnamp;amp;lsquo;amp;amp;lsquo; the location of the
data. This way we (i) do not need a metric (or even stronger structure)
-- pairwise dissimilarities suffice; and additionally (ii) produce
low-dimensional embeddings that can be analyzed visually.
We achieve this by combining an entropy-based embedding method
with an entropy-based version of semi-supervised logistic regression.
We present results for clustering and semi-supervised classification.