Efficient learning with privileged information in nonlinear time series

Examensarbete för masterexamen

Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.12380/304890
Download file(s):
File Description SizeFormat 
CSE 22-47 Jung.pdf7.06 MBAdobe PDFView/Open
Full metadata record
DC FieldValueLanguage
dc.contributor.authorJung, Bastian-
dc.contributor.departmentChalmers tekniska högskola / Institutionen för data och informationstekniksv
dc.date.accessioned2022-06-23T12:26:07Z-
dc.date.available2022-06-23T12:26:07Z-
dc.date.issued2022sv
dc.date.submitted2020-
dc.identifier.urihttps://hdl.handle.net/20.500.12380/304890-
dc.description.abstractIn domains where sample sizes are limited, efficient learning algorithms are critical. Learning using privileged information (LuPI) offers increased sample efficiency by allowing prediction models access to information at training time that is unavailable when the models are used. In recent work, it was shown that for prediction in linear- Gaussian dynamical systems, a LuPI learner with access to intermediate time series data is never worse and often better in expectation than any unbiased classical learner. We provide new insights into this analysis and generalize it to nonlinear prediction tasks in latent dynamical systems, extending theoretical guarantees to the case where the map connecting latent variables and observations is known up to a linear transform. In addition, we propose algorithms based on random features and representation learning for the case when this map is unknown. A suite of empirical results confirm theoretical findings and show the potential of using privileged timeseries information in nonlinear prediction.sv
dc.language.isoengsv
dc.setspec.uppsokTechnology-
dc.subjectMachine Learningsv
dc.subjectPrivileged Informationsv
dc.subjectTime Seriessv
dc.subjectSample Efficiencysv
dc.subjectLatent Dynamical Systemssv
dc.titleEfficient learning with privileged information in nonlinear time seriessv
dc.type.degreeExamensarbete för masterexamensv
dc.type.uppsokH-
dc.contributor.examinerAxelson-Fisk, Marina-
dc.contributor.supervisorJohansson, Fredrik-
dc.identifier.coursecodeDATX05sv
Collection:Examensarbeten för masterexamen // Master Theses



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.