Show simple item record  

dc.contributor.authorGouk, Henryen_NZ
dc.contributor.authorPfahringer, Bernharden_NZ
dc.contributor.authorFrank, Eibeen_NZ
dc.contributor.editorLee, Wee Sunen_NZ
dc.contributor.editorSuzuki, Taijien_NZ
dc.coverage.spatialNagoya, Japanen_NZ
dc.date.accessioned2019-11-24T22:40:18Z
dc.date.available2019en_NZ
dc.date.available2019-11-24T22:40:18Z
dc.date.issued2019en_NZ
dc.identifier.citationGouk, H., Pfahringer, B., & Frank, E. (2019). Stochastic gradient trees. In W. S. Lee & T. Suzuki (Eds.), Proceedings of 11th Asian Conference on Machine Learning (ACML 2019) (Vol. PMLR 101, pp. 1094–1109). Nagoya, Japan: PMLR.en
dc.identifier.urihttps://hdl.handle.net/10289/13189
dc.description.abstractWe present an algorithm for learning decision trees using stochastic gradient information as the source of supervision. In contrast to previous approaches to gradient-based tree learning, our method operates in the incremental learning setting rather than the batch learning setting, and does not make use of soft splits or require the construction of a new tree for every update. We demonstrate how one can apply these decision trees to different problems by changing only the loss function, using classification, regression, and multi-instance learning as example applications. In the experimental evaluation, our method performs similarly to standard incremental classification trees, outperforms state of the art incremental regression trees, and achieves comparable performance with batch multi-instance learning methods.
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherPMLRen_NZ
dc.relation.urihttp://proceedings.mlr.press/v101/gouk19a.htmlen_NZ
dc.rights© 2019 H. Gouk, B. Pfahringer & E. Frank.
dc.subjectDecision tree induction
dc.subjectgradient-based optimisation
dc.subjectdata stream mining
dc.subjectmulti-instance learning
dc.subjectMachine learning
dc.titleStochastic gradient treesen_NZ
dc.typeConference Contribution
dc.relation.isPartOfProceedings of 11th Asian Conference on Machine Learning (ACML 2019)en_NZ
pubs.begin-page1094
pubs.elements-id249463
pubs.end-page1109
pubs.finish-date2019-11-19en_NZ
pubs.publisher-urlhttp://proceedings.mlr.press/v101/en_NZ
pubs.start-date2019-11-17en_NZ
pubs.volumePMLR 101en_NZ


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record