Relating Function Class Complexity and Cluster Structure in the Function Domain with Applications to Transduction

Guy Lever
Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, PMLR 9:437-444, 2010.

Abstract

We relate function class complexity to structure in the function domain. This facilitates risk analysis relative to cluster structure in the input space which is particularly effective in semi-supervised learning. In particular we quantify the complexity of function classes defined over a graph in terms of the graph structure.

Cite this Paper

BibTeX
@InProceedings{pmlr-v9-lever10a, title = {Relating Function Class Complexity and Cluster Structure in the Function Domain with Applications to Transduction}, author = {Lever, Guy}, booktitle = {Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics}, pages = {437--444}, year = {2010}, editor = {Teh, Yee Whye and Titterington, Mike}, volume = {9}, series = {Proceedings of Machine Learning Research}, address = {Chia Laguna Resort, Sardinia, Italy}, month = {13--15 May}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v9/lever10a/lever10a.pdf}, url = {https://proceedings.mlr.press/v9/lever10a.html}, abstract = {We relate function class complexity to structure in the function domain. This facilitates risk analysis relative to cluster structure in the input space which is particularly effective in semi-supervised learning. In particular we quantify the complexity of function classes defined over a graph in terms of the graph structure.} }
Endnote
%0 Conference Paper %T Relating Function Class Complexity and Cluster Structure in the Function Domain with Applications to Transduction %A Guy Lever %B Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2010 %E Yee Whye Teh %E Mike Titterington %F pmlr-v9-lever10a %I PMLR %P 437--444 %U https://proceedings.mlr.press/v9/lever10a.html %V 9 %X We relate function class complexity to structure in the function domain. This facilitates risk analysis relative to cluster structure in the input space which is particularly effective in semi-supervised learning. In particular we quantify the complexity of function classes defined over a graph in terms of the graph structure.
RIS
TY - CPAPER TI - Relating Function Class Complexity and Cluster Structure in the Function Domain with Applications to Transduction AU - Guy Lever BT - Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics DA - 2010/03/31 ED - Yee Whye Teh ED - Mike Titterington ID - pmlr-v9-lever10a PB - PMLR DP - Proceedings of Machine Learning Research VL - 9 SP - 437 EP - 444 L1 - http://proceedings.mlr.press/v9/lever10a/lever10a.pdf UR - https://proceedings.mlr.press/v9/lever10a.html AB - We relate function class complexity to structure in the function domain. This facilitates risk analysis relative to cluster structure in the input space which is particularly effective in semi-supervised learning. In particular we quantify the complexity of function classes defined over a graph in terms of the graph structure. ER -
APA
Lever, G.. (2010). Relating Function Class Complexity and Cluster Structure in the Function Domain with Applications to Transduction. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 9:437-444 Available from https://proceedings.mlr.press/v9/lever10a.html.

Related Material