de.mpg.escidoc.pubman.appbase.FacesBean
English
 
Help Guide Disclaimer Contact us Login
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Journal Article

Regularized principal manifolds

MPS-Authors
http://pubman.mpdl.mpg.de/cone/persons/resource/persons84193

Mika S, Schölkopf,  B
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)
There are no public fulltexts available
Supplementary Material (public)
There is no public supplementary material available
Citation

Smola, A., Mika S, Schölkopf, B., & Williamson, R. (2001). Regularized principal manifolds. Journal of Machine Learning Research, 1, 179-209. Retrieved from http://jmlr.csail.mit.edu/papers/volume1/smola01a/smola01a.pdf.


Cite as: http://hdl.handle.net/11858/00-001M-0000-0013-E26A-9
Abstract
Many settings of unsupervised learning can be viewed as quantization problems - the minimization of the expected quantization error subject to some restrictions. This allows the use of tools such as regularization from the theory of (supervised) risk minimization for unsupervised learning. This setting turns out to be closely related to principal curves, the generative topographic map, and robust coding. We explore this connection in two ways: (1) we propose an algorithm for finding principal manifolds that can be regularized in a variety of ways; and (2) we derive uniform convergence bounds and hence bounds on the learning rates of the algorithm. In particular, we give bounds on the covering numbers which allows us to obtain nearly optimal learning rates for certain types of regularization operators. Experimental results demonstrate the feasibility of the approach.