Search: WFRF:(Kjellström Hedvig 1973 ) >
Aligned Multi-Task ...
Aligned Multi-Task Gaussian Process
-
- Mikheeva, Olga (author)
- KTH,Robotik, perception och lärande, RPL
-
- Kazlauskaite, Ieva (author)
- University of Cambridge, University of Cambridge
-
- Hartshorne, Adam (author)
- University of Bath, University of Bath
-
show more...
-
- Kjellström, Hedvig, 1973- (author)
- KTH,Robotik, perception och lärande, RPL
-
- Ek, Carl Henrik (author)
- University of Cambridge, University of Cambridge
-
- Campbell, Neill D.F. (author)
- University of Bath, University of Bath
-
show less...
-
(creator_code:org_t)
- ML Research Press, 2022
- 2022
- English.
-
In: Proceedings of the 25th International Conference on Artificial Intelligence and Statistics, AISTATS 2022. - : ML Research Press. ; , s. 2970-2988
- Related links:
-
https://urn.kb.se/re...
Abstract
Subject headings
Close
- Multi-task learning requires accurate identification of the correlations between tasks. In real-world time-series, tasks are rarely perfectly temporally aligned; traditional multitask models do not account for this and subsequent errors in correlation estimation will result in poor predictive performance and uncertainty quantification. We introduce a method that automatically accounts for temporal misalignment in a unified generative model that improves predictive performance. Our method uses Gaussian processes (GPs) to model the correlations both within and between the tasks. Building on the previous work by Kazlauskaite et al. (2019), we include a separate monotonic warp of the input data to model temporal misalignment. In contrast to previous work, we formulate a lower bound that accounts for uncertainty in both the estimates of the warping process and the underlying functions. Also, our new take on a monotonic stochastic process, with efficient path-wise sampling for the warp functions, allows us to perform full Bayesian inference in the model rather than MAP estimates. Missing data experiments, on synthetic and real time-series, demonstrate the advantages of accounting for misalignments (vs standard unaligned method) as well as modelling the uncertainty in the warping process (vs baseline MAP alignment approach).
Subject headings
- NATURVETENSKAP -- Matematik -- Sannolikhetsteori och statistik (hsv//swe)
- NATURAL SCIENCES -- Mathematics -- Probability Theory and Statistics (hsv//eng)
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Reglerteknik (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Control Engineering (hsv//eng)
Publication and Content Type
- ref (subject category)
- kon (subject category)
To the university's database