Efficient learning with privileged information in nonlinear time series

Examensarbete för masterexamen

Använd denna länk för att citera eller länka till detta dokument: https://hdl.handle.net/20.500.12380/304890
Ladda ner:
Fil Beskrivning StorlekFormat 
CSE 22-47 Jung.pdf7.06 MBAdobe PDFVisa
Bibliografiska detaljer
FältVärde
Typ: Examensarbete för masterexamen
Titel: Efficient learning with privileged information in nonlinear time series
Författare: Jung, Bastian
Sammanfattning: In 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.
Nyckelord: Machine Learning;Privileged Information;Time Series;Sample Efficiency;Latent Dynamical Systems
Utgivningsdatum: 2022
Utgivare: Chalmers tekniska högskola / Institutionen för data och informationsteknik
URI: https://hdl.handle.net/20.500.12380/304890
Samling:Examensarbeten för masterexamen // Master Theses



Materialet i Chalmers öppna arkiv är upphovsrättsligt skyddat och får ej användas i kommersiellt syfte!