Arenz, Oleg ; Neumann, Gerhard ; Zhong, Mingjun (2018)
Efficient Gradient-Free Variational Inference using Policy Search.
35th International Conference on Machine Learning (ICML 2018). Stockholm, Sweden (10.-15.07.2018)
Konferenzveröffentlichung, Bibliographie
Dies ist die neueste Version dieses Eintrags.
Kurzbeschreibung (Abstract)
Inference from complex distributions is a common problem in machine learning needed for many Bayesian methods. We propose an efficient, gradient-free method for learning general GMM approximations of multimodal distributions based on recent insights from stochastic search methods. Our method establishes information-geometric trust regions to ensure efficient exploration of the sampling space and stability of the GMM updates, allowing for efficient estimation of multi-variate Gaussian variational distributions. For GMMs, we apply a variational lower bound to decompose the learning objective into sub-problems given by learning the individual mixture components and the coefficients. The number of mixture components is adapted online in order to allow for arbitrary exact approximations. We demonstrate on several domains that we can learn significantly better approximations than competing variational inference methods and that the quality of samples drawn from our approximations is on par with samples created by state-of-the-art MCMC samplers that require significantly more computational resources.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2018 |
| Autor(en): | Arenz, Oleg ; Neumann, Gerhard ; Zhong, Mingjun |
| Art des Eintrags: | Bibliographie |
| Titel: | Efficient Gradient-Free Variational Inference using Policy Search |
| Sprache: | Englisch |
| Publikationsjahr: | 2018 |
| Ort: | Darmstadt |
| Verlag: | PMLR |
| Buchtitel: | Proceedings of Machine Learning Research |
| Band einer Reihe: | 80 |
| Kollation: | 10 ungezählte Seiten |
| Veranstaltungstitel: | 35th International Conference on Machine Learning (ICML 2018) |
| Veranstaltungsort: | Stockholm, Sweden |
| Veranstaltungsdatum: | 10.-15.07.2018 |
| Zugehörige Links: | |
| Kurzbeschreibung (Abstract): | Inference from complex distributions is a common problem in machine learning needed for many Bayesian methods. We propose an efficient, gradient-free method for learning general GMM approximations of multimodal distributions based on recent insights from stochastic search methods. Our method establishes information-geometric trust regions to ensure efficient exploration of the sampling space and stability of the GMM updates, allowing for efficient estimation of multi-variate Gaussian variational distributions. For GMMs, we apply a variational lower bound to decompose the learning objective into sub-problems given by learning the individual mixture components and the coefficients. The number of mixture components is adapted online in order to allow for arbitrary exact approximations. We demonstrate on several domains that we can learn significantly better approximations than competing variational inference methods and that the quality of samples drawn from our approximations is on par with samples created by state-of-the-art MCMC samplers that require significantly more computational resources. |
| Freie Schlagworte: | Machine Learning, ICML, Variational Inference, Sampling, Policy Search, MCMC, Markov Chain Monte Carlo |
| Zusätzliche Informationen: | Presentation video: https://vimeo.com/294656117 |
| 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: | 02 Aug 2024 12:46 |
| Letzte Änderung: | 02 Aug 2024 12:46 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
Verfügbare Versionen dieses Eintrags
-
Efficient Gradient-Free Variational Inference using Policy Search. (deposited 02 Dez 2022 12:46)
- Efficient Gradient-Free Variational Inference using Policy Search. (deposited 02 Aug 2024 12:46) [Gegenwärtig angezeigt]
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum