Controlling Moments with Kernel Stein Discrepancies
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2022
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909657000312832 |
|---|---|
| author | Kanagawa, Heishiro Barp, Alessandro Gretton, Arthur Mackey, Lester |
| author_facet | Kanagawa, Heishiro Barp, Alessandro Gretton, Arthur Mackey, Lester |
| contents | Kernel Stein discrepancies (KSDs) measure the quality of a distributional approximation and can be computed even when the target density has an intractable normalizing constant. Notable applications include the diagnosis of approximate MCMC samplers and goodness-of-fit tests for unnormalized statistical models. The present work analyzes the convergence control properties of KSDs. We first show that standard KSDs used for weak convergence control fail to control moment convergence. To address this limitation, we next provide sufficient conditions under which alternative diffusion KSDs control both moment and weak convergence. As an immediate consequence we develop, for each $q > 0$, the first KSDs known to exactly characterize $q$-Wasserstein convergence. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2211_05408 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Controlling Moments with Kernel Stein Discrepancies Kanagawa, Heishiro Barp, Alessandro Gretton, Arthur Mackey, Lester Machine Learning Computation Kernel Stein discrepancies (KSDs) measure the quality of a distributional approximation and can be computed even when the target density has an intractable normalizing constant. Notable applications include the diagnosis of approximate MCMC samplers and goodness-of-fit tests for unnormalized statistical models. The present work analyzes the convergence control properties of KSDs. We first show that standard KSDs used for weak convergence control fail to control moment convergence. To address this limitation, we next provide sufficient conditions under which alternative diffusion KSDs control both moment and weak convergence. As an immediate consequence we develop, for each $q > 0$, the first KSDs known to exactly characterize $q$-Wasserstein convergence. |
| title | Controlling Moments with Kernel Stein Discrepancies |
| topic | Machine Learning Computation |
| url | https://arxiv.org/abs/2211.05408 |