Abstract
Goodness-of-fit testing is often criticized for its lack of practical relevance; since ``all models are wrong’, the null hypothesis that the data conform to our model is ultimately always rejected when the sample size is large enough. Despite this, probabilistic models are still used extensively, raising the more pertinent question of whether the model is good enough for a specific task. This question can be formalized as a robust goodness-of-fit testing problem by asking whether the data were generated by a distribution corresponding to our model up to some mild perturbation. In this paper, we show that existing kernel goodness-of-fit tests are not robust according to common notions of robustness including qualitative and quantitative robustness. We also show that robust techniques based on tilted kernels from the parameter estimation literature are not sufficient for ensuring both types of robustness in the context of goodness-of-fit testing. We therefore propose the first robust kernel goodness-of-fit test which resolves this open problem using kernel Stein discrepancy balls, which encompass perturbation models such as Huber contamination models and density uncertainty bands.
