Consistency of Nearest Neighbor Classification under Selective Sampling

Sanjoy Dasgupta
Proceedings of the 25th Annual Conference on Learning Theory, PMLR 23:18.1-18.15, 2012.

Abstract

This paper studies nearest neighbor classification in a model where unlabeled data points arrive in a stream, and the learner decides, for each one, whether to ask for its label. Are there generic ways to augment or modify any selective sampling strategy so as to ensure the consistency of the resulting nearest neighbor classifier?

Cite this Paper

BibTeX
@InProceedings{pmlr-v23-dasgupta12, title = {Consistency of Nearest Neighbor Classification under Selective Sampling}, author = {Dasgupta, Sanjoy}, booktitle = {Proceedings of the 25th Annual Conference on Learning Theory}, pages = {18.1--18.15}, year = {2012}, editor = {Mannor, Shie and Srebro, Nathan and Williamson, Robert C.}, volume = {23}, series = {Proceedings of Machine Learning Research}, address = {Edinburgh, Scotland}, month = {25--27 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v23/dasgupta12/dasgupta12.pdf}, url = {https://proceedings.mlr.press/v23/dasgupta12.html}, abstract = {This paper studies nearest neighbor classification in a model where unlabeled data points arrive in a stream, and the learner decides, for each one, whether to ask for its label. Are there generic ways to augment or modify any selective sampling strategy so as to ensure the consistency of the resulting nearest neighbor classifier?} }
Endnote
%0 Conference Paper %T Consistency of Nearest Neighbor Classification under Selective Sampling %A Sanjoy Dasgupta %B Proceedings of the 25th Annual Conference on Learning Theory %C Proceedings of Machine Learning Research %D 2012 %E Shie Mannor %E Nathan Srebro %E Robert C. Williamson %F pmlr-v23-dasgupta12 %I PMLR %P 18.1--18.15 %U https://proceedings.mlr.press/v23/dasgupta12.html %V 23 %X This paper studies nearest neighbor classification in a model where unlabeled data points arrive in a stream, and the learner decides, for each one, whether to ask for its label. Are there generic ways to augment or modify any selective sampling strategy so as to ensure the consistency of the resulting nearest neighbor classifier?
RIS
TY - CPAPER TI - Consistency of Nearest Neighbor Classification under Selective Sampling AU - Sanjoy Dasgupta BT - Proceedings of the 25th Annual Conference on Learning Theory DA - 2012/06/16 ED - Shie Mannor ED - Nathan Srebro ED - Robert C. Williamson ID - pmlr-v23-dasgupta12 PB - PMLR DP - Proceedings of Machine Learning Research VL - 23 SP - 18.1 EP - 18.15 L1 - http://proceedings.mlr.press/v23/dasgupta12/dasgupta12.pdf UR - https://proceedings.mlr.press/v23/dasgupta12.html AB - This paper studies nearest neighbor classification in a model where unlabeled data points arrive in a stream, and the learner decides, for each one, whether to ask for its label. Are there generic ways to augment or modify any selective sampling strategy so as to ensure the consistency of the resulting nearest neighbor classifier? ER -
APA
Dasgupta, S.. (2012). Consistency of Nearest Neighbor Classification under Selective Sampling. Proceedings of the 25th Annual Conference on Learning Theory, in Proceedings of Machine Learning Research 23:18.1-18.15 Available from https://proceedings.mlr.press/v23/dasgupta12.html.

Related Material