Diameter-based Interactive Structure Discovery

Christopher Tosh, Daniel Hsu
; Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, PMLR 108:580-590, 2020.

Abstract

We introduce interactive structure discovery, a generic framework that encompasses many interactive learning settings, including active learning, top-k item identification, interactive drug discovery, and others. We adapt a recently developed active learning algorithm of Tosh and Dasgupta for interactive structure discovery, and show that the new algorithm can be made noise-tolerant and enjoys favorable query complexity bounds.

Cite this Paper


BibTeX
@InProceedings{pmlr-v108-tosh20a, title = {Diameter-based Interactive Structure Discovery}, author = {Tosh, Christopher and Hsu, Daniel}, pages = {580--590}, year = {2020}, editor = {Silvia Chiappa and Roberto Calandra}, volume = {108}, series = {Proceedings of Machine Learning Research}, address = {Online}, month = {26--28 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v108/tosh20a/tosh20a.pdf}, url = {http://proceedings.mlr.press/v108/tosh20a.html}, abstract = {We introduce interactive structure discovery, a generic framework that encompasses many interactive learning settings, including active learning, top-k item identification, interactive drug discovery, and others. We adapt a recently developed active learning algorithm of Tosh and Dasgupta for interactive structure discovery, and show that the new algorithm can be made noise-tolerant and enjoys favorable query complexity bounds.} }
Endnote
%0 Conference Paper %T Diameter-based Interactive Structure Discovery %A Christopher Tosh %A Daniel Hsu %B Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2020 %E Silvia Chiappa %E Roberto Calandra %F pmlr-v108-tosh20a %I PMLR %J Proceedings of Machine Learning Research %P 580--590 %U http://proceedings.mlr.press %V 108 %W PMLR %X We introduce interactive structure discovery, a generic framework that encompasses many interactive learning settings, including active learning, top-k item identification, interactive drug discovery, and others. We adapt a recently developed active learning algorithm of Tosh and Dasgupta for interactive structure discovery, and show that the new algorithm can be made noise-tolerant and enjoys favorable query complexity bounds.
APA
Tosh, C. & Hsu, D.. (2020). Diameter-based Interactive Structure Discovery. Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, in PMLR 108:580-590

Related Material