KIT | KIT-Bibliothek | Impressum | Datenschutz

Trust-Region Variational Inference with Gaussian Mixture Models

Arenz, O.; Zhong, M.; Neumann, G.

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-theart MCMC samplers while requiring up to three orders of magnitude less computational resources.

Open Access Logo

Verlagsausgabe §
DOI: 10.5445/IR/1000124510
Veröffentlicht am 13.10.2020
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Publikationstyp Zeitschriftenaufsatz
Publikationsmonat/-jahr 09.2020
Sprache Englisch
Identifikator ISSN: 1532-4435, 1533-7928
KITopen-ID: 1000124510
Erschienen in Journal of machine learning research
Verlag Journal of Machine Learning Research
Band 21
Seiten 1-60
Schlagwörter approximate inference, variational inference, sampling, policy search, mcmc, markov chain monte carlo
Nachgewiesen in Scopus
Web of Science
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page