Learning a kernel matrix for nonlinear dimensionality reduction


We investigate how to learn a kernel matrix for high dimensional data that lies on or near a low dimensional manifold. Noting that the kernel matrix implicitly maps the data into a nonlinear feature space, we show how to discover a mapping that "unfolds" the underlying manifold from which the data was sampled. The kernel matrix is constructed by maximizing the variance in feature space subject to local constraints that preserve the angles and distances between nearest neighbors. The main optimization involves an instance of semidefinite programming---a fundamentally different computation than previous algorithms for manifold learning, such as Isomap and locally linear embedding. The optimized kernels perform better than polynomial and Gaussian kernels for problems in manifold learning, but worse for problems in large margin classification. We explain these results in terms of the geometric properties of different kernels and comment on various interpretations of other manifold learning algorithms as kernel methods.

DOI: 10.1145/1015330.1015345

Extracted Key Phrases

8 Figures and Tables

Citations per Year

550 Citations

Semantic Scholar estimates that this publication has 550 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Weinberger2004LearningAK, title={Learning a kernel matrix for nonlinear dimensionality reduction}, author={Kilian Q. Weinberger and Fei Sha and Lawrence K. Saul}, booktitle={ICML}, year={2004} }