Diameter-Based Active Learning

Christopher Tosh, Sanjoy Dasgupta
; Proceedings of the 34th International Conference on Machine Learning, PMLR 70:3444-3452, 2017.

Abstract

To date, the tightest upper and lower-bounds for the active learning of general concept classes have been in terms of a parameter of the learning problem called the splitting index. We provide, for the first time, an efficient algorithm that is able to realize this upper bound, and we empirically demonstrate its good performance.

Cite this Paper


BibTeX
@InProceedings{pmlr-v70-tosh17a, title = {Diameter-Based Active Learning}, author = {Christopher Tosh and Sanjoy Dasgupta}, pages = {3444--3452}, year = {2017}, editor = {Doina Precup and Yee Whye Teh}, volume = {70}, series = {Proceedings of Machine Learning Research}, address = {International Convention Centre, Sydney, Australia}, month = {06--11 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v70/tosh17a/tosh17a.pdf}, url = {http://proceedings.mlr.press/v70/tosh17a.html}, abstract = {To date, the tightest upper and lower-bounds for the active learning of general concept classes have been in terms of a parameter of the learning problem called the splitting index. We provide, for the first time, an efficient algorithm that is able to realize this upper bound, and we empirically demonstrate its good performance.} }
Endnote
%0 Conference Paper %T Diameter-Based Active Learning %A Christopher Tosh %A Sanjoy Dasgupta %B Proceedings of the 34th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2017 %E Doina Precup %E Yee Whye Teh %F pmlr-v70-tosh17a %I PMLR %J Proceedings of Machine Learning Research %P 3444--3452 %U http://proceedings.mlr.press %V 70 %W PMLR %X To date, the tightest upper and lower-bounds for the active learning of general concept classes have been in terms of a parameter of the learning problem called the splitting index. We provide, for the first time, an efficient algorithm that is able to realize this upper bound, and we empirically demonstrate its good performance.
APA
Tosh, C. & Dasgupta, S.. (2017). Diameter-Based Active Learning. Proceedings of the 34th International Conference on Machine Learning, in PMLR 70:3444-3452

Related Material