Arenz, Oleg ; Zhong, Mingjun ; Neumann, Gerhard (2022)
Trust-Region Variational Inference with Gaussian Mixture Models.
In: Journal of Machine Learning Research, 2020, 21
doi: 10.26083/tuprints-00022920
Artikel, Zweitveröffentlichung, Verlagsversion
 | Es ist eine neuere Version dieses Eintrags verfügbar. |
Kurzbeschreibung (Abstract)
Many methods for machine learning rely on approximate inference from intractable probability distributions. Variational inference approximates such distributions by tractable models that can be subsequently used for approximate inference. Learning sufficiently accurate approximations requires a rich model family and careful exploration of the relevant modes of the target distribution. We propose a method for learning accurate GMM approximations of intractable probability distributions based on insights from policy search by using information-geometric trust regions for principled exploration. For efficient improvement of the GMM approximation, we derive a lower bound on the corresponding optimization objective enabling us to update the components independently. Our use of the lower bound ensures convergence to a stationary point of the original objective. The number of components is adapted online by adding new components in promising regions and by deleting components with negligible weight. We demonstrate on several domains that we can learn approximations of complex, multimodal distributions with a quality that is unmet by previous variational inference methods, and that the GMM approximation can be used for drawing samples that are on par with samples created by state-of-the-art MCMC samplers while requiring up to three orders of magnitude less computational resources.
| Typ des Eintrags: | Artikel |
|---|---|
| Erschienen: | 2022 |
| Autor(en): | Arenz, Oleg ; Zhong, Mingjun ; Neumann, Gerhard |
| Art des Eintrags: | Zweitveröffentlichung |
| Titel: | Trust-Region Variational Inference with Gaussian Mixture Models |
| Sprache: | Englisch |
| Publikationsjahr: | 2022 |
| Ort: | Darmstadt |
| Publikationsdatum der Erstveröffentlichung: | 2020 |
| Verlag: | JMLR |
| Titel der Zeitschrift, Zeitung oder Schriftenreihe: | Journal of Machine Learning Research |
| Jahrgang/Volume einer Zeitschrift: | 21 |
| Kollation: | 60 Seiten |
| DOI: | 10.26083/tuprints-00022920 |
| URL / URN: | https://tuprints.ulb.tu-darmstadt.de/22920 |
| Zugehörige Links: | |
| Herkunft: | Zweitveröffentlichungsservice |
| Kurzbeschreibung (Abstract): | Many methods for machine learning rely on approximate inference from intractable probability distributions. Variational inference approximates such distributions by tractable models that can be subsequently used for approximate inference. Learning sufficiently accurate approximations requires a rich model family and careful exploration of the relevant modes of the target distribution. We propose a method for learning accurate GMM approximations of intractable probability distributions based on insights from policy search by using information-geometric trust regions for principled exploration. For efficient improvement of the GMM approximation, we derive a lower bound on the corresponding optimization objective enabling us to update the components independently. Our use of the lower bound ensures convergence to a stationary point of the original objective. The number of components is adapted online by adding new components in promising regions and by deleting components with negligible weight. We demonstrate on several domains that we can learn approximations of complex, multimodal distributions with a quality that is unmet by previous variational inference methods, and that the GMM approximation can be used for drawing samples that are on par with samples created by state-of-the-art MCMC samplers while requiring up to three orders of magnitude less computational resources. |
| Freie Schlagworte: | approximate inference, variational inference, sampling, policy search, mcmc, markov chain monte carlo |
| Status: | Verlagsversion |
| URN: | urn:nbn:de:tuda-tuprints-229205 |
| Sachgruppe der Dewey Dezimalklassifikatin (DDC): | 000 Allgemeines, Informatik, Informationswissenschaft > 004 Informatik |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Intelligente Autonome Systeme |
| Hinterlegungsdatum: | 25 Nov 2022 12:42 |
| Letzte Änderung: | 24 Mai 2023 09:34 |
| PPN: | 503637777 |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
Verfügbare Versionen dieses Eintrags
- Trust-Region Variational Inference with Gaussian Mixture Models. (deposited 25 Nov 2022 12:42) [Gegenwärtig angezeigt]
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum