Similarity measure for sparse time course data based on Gaussian processes
File(s)
Accepted version
Author(s)
Liu, Zijing
Barahona, Mauricio
Type
Conference Paper
Abstract
We propose a similarity measure for sparsely sampled time course data in the form of a log-likelihood ratio of Gaussian processes (GP). The proposed GP similarity is similar to a Bayes factor and provides enhanced robustness to noise in sparse time series, such as those found in various biological settings, e.g., gene transcriptomics. We show that the GP measure is equivalent to the Euclidean distance when the noise variance in the GP is negligible compared to the noise variance of the signal. Our numerical experiments on both synthetic and real data show improved performance of the GP similarity when used in conjunction with two distance-based clustering methods.
Date Issued
2021-12-01
Date Acceptance
2021-05-12
Citation
Proceedings of Machine Learning Research (PMLR) - Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence (UAI), 2021, 161, pp.1332-1341
Publisher
PMLR
Start Page
1332
End Page
1341
Journal / Book Title
Proceedings of Machine Learning Research (PMLR) - Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence (UAI)
Volume
161
Copyright Statement
© 2021 The Author(s).
Sponsor
Engineering & Physical Science Research Council (EPSRC)
Identifier
https://proceedings.mlr.press/v161/liu21a.html
Grant Number
EP/N014529/1
Source
Uncertainty in Artificial Intelligence 2021
Subjects
cs.LG
cs.LG
cs.IR
stat.ML
Publication Status
Published
Start Date
2921-07-27
Finish Date
2021-07-30
Date Publish Online
2021-12-01