Using perturbation to improve goodness-of-fit tests based on kernelized Stein discrepancy
File(s)
Published version
OA Location
Author(s)
Liu, Xing
Duncan, Andrew
Gandy, Axel
Type
Conference Paper
Abstract
Kernelized Stein discrepancy (KSD) is a score-based discrepancy widely used in goodness-of-fit tests. It can be applied even when the target distribution has an unknown normalising factor, such as in Bayesian analysis. We show theoretically and empirically that the KSD test can suffer from low power when the target and the alternative distributions have the same well-separated modes but differ in mixing proportions. We propose to perturb the observed sample via Markov transition kernels, with respect to which the target distribution is invariant. This allows us to then employ the KSD test on the perturbed sample. We provide numerical evidence that with suitably chosen transition kernels the proposed approach can lead to substantially higher power than the KSD test.
Date Issued
2023-07-23
Date Acceptance
2023-04-24
Citation
Proceedings of Machine Learning Research, 2023, 202
ISSN
2640-3498
Publisher
MLResearchPress
Journal / Book Title
Proceedings of Machine Learning Research
Volume
202
Copyright Statement
© The authors and PMLR 2023. MLResearchPress.
Sponsor
Imperial College London
Source
Fortieth International Conference on Machine Learning
Publication Status
Published
Start Date
2023-07-23
Finish Date
2023-07-29
Coverage Spatial
Honolulu, Hawaii
Date Publish Online
2023-05-01