Diffusion models for probabilistic programming


METADATA ONLY
Loading...

Date

2023-12-15

Publication Type

Conference Poster

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

We propose Diffusion Model Variational Inference (DMVI), a novel method for automated approximate inference in probabilistic programming languages (PPLs). DMVI utilizes diffusion models as variational approximations to the true posterior distribution by deriving a novel bound to the marginal likelihood objective used in Bayesian modelling. DMVI is easy to implement, allows hassle-free inference in PPLs without the drawbacks of, e.g., variational inference using normalizing flows, and does not make any constraints on the underlying neural network model. We evaluate DMVI on a set of common Bayesian models and show that its posterior inferences are in general more accurate than those of contemporary methods used in PPLs while having a similar computational cost and requiring less manual tuning.

Permanent link

Publication status

unpublished

Editor

Book title

Journal / series

Volume

Pages / Article No.

Publisher

Event

Workshop on Diffusion Models @ NeurIPS 2023

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Machine Learning (cs.LG); Machine Learning (stat.ML); FOS: Computer and information sciences

Organisational unit

02286 - Swiss Data Science Center (SDSC) / Swiss Data Science Center (SDSC) check_circle

Notes

Funding

Related publications and datasets

Is new version of: 10.48550/ARXIV.2311.00474