TU Darmstadt / ULB / TUprints

Efficient Gradient-Free Variational Inference using Policy Search

Arenz, Oleg ; Neumann, Gerhard ; Zhong, Mingjun (2022)
Efficient Gradient-Free Variational Inference using Policy Search.
35th International Conference on Machine Learning (ICML 2018). Stockholm, Sweden (10.-15.07.2018)
doi: 10.26083/tuprints-00022925
Conference or Workshop Item, Secondary publication, Publisher's Version

[img] Text
arenz18a.pdf
Copyright Information: CC BY 4.0 International - Creative Commons, Attribution.

Download (3MB)
[img] Text (Supplementary PDF)
arenz18a-supp.pdf
Copyright Information: CC BY 4.0 International - Creative Commons, Attribution.

Download (289kB)
Item Type: Conference or Workshop Item
Type of entry: Secondary publication
Title: Efficient Gradient-Free Variational Inference using Policy Search
Language: English
Date: 2022
Place of Publication: Darmstadt
Year of primary publication: 2018
Publisher: PMLR
Book Title: Proceedings of Machine Learning Research
Series Volume: 80
Collation: 10 ungezählte Seiten
Event Title: 35th International Conference on Machine Learning (ICML 2018)
Event Location: Stockholm, Sweden
Event Dates: 10.-15.07.2018
DOI: 10.26083/tuprints-00022925
Corresponding Links:
Origin: Secondary publication service
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.

Uncontrolled Keywords: Machine Learning, ICML, Variational Inference, Sampling, Policy Search, MCMC, Markov Chain Monte Carlo
Status: Publisher's Version
URN: urn:nbn:de:tuda-tuprints-229250
Additional Information:

Presentation video: https://vimeo.com/294656117

Classification DDC: 000 Generalities, computers, information > 004 Computer science
Divisions: 20 Department of Computer Science > Intelligent Autonomous Systems
Date Deposited: 02 Dec 2022 12:46
Last Modified: 16 Jan 2023 06:46
URI: https://tuprints.ulb.tu-darmstadt.de/id/eprint/22925
PPN: 503359734
Export:
Actions (login required)
View Item View Item