Jonas Wildberger
Flow Matching for Scalable Simulation-Based Inference
Wildberger, Jonas; Dax, Maximilian; Green, Stephen; Buchholz, Simon; Macke, Jakob; Schölkopf, Bernhard
Authors
Maximilian Dax
Dr STEPHEN GREEN STEPHEN.GREEN2@NOTTINGHAM.AC.UK
Nottingham Research Fellow
Simon Buchholz
Jakob Macke
Bernhard Schölkopf
Abstract
Neural posterior estimation methods based on discrete normalizing flows have become established tools for simulation-based inference (SBI), but scaling them to high-dimensional problems can be challenging. Building on recent advances in generative modeling, we here present flow matching posterior estimation (FMPE), a technique for SBI using continuous normalizing flows. Like diffusion models, and in contrast to discrete flows, flow matching allows for unconstrained architectures, providing enhanced flexibility for complex data modalities. Flow matching, therefore, enables exact density evaluation, fast training, and seamless scalability to large architectures—making it ideal for SBI. We show that FMPE achieves competitive performance on an established SBI benchmark, and then demonstrate its improved scalability on a challenging scientific problem: for gravitational-wave in- ference, FMPE outperforms methods based on comparable discrete flows, reducing training time by 30% with substantially improved accuracy. Our work underscores the potential of FMPE to enhance performance in challenging inference scenarios, thereby paving the way for more advanced applications to scientific problems.
Citation
Wildberger, J., Dax, M., Green, S., Buchholz, S., Macke, J., & Schölkopf, B. (2023, December). Flow Matching for Scalable Simulation-Based Inference. Poster presented at Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), New Orleans, USA
Presentation Conference Type | Poster |
---|---|
Conference Name | Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023) |
Start Date | Dec 10, 2023 |
End Date | Dec 16, 2023 |
Deposit Date | Feb 8, 2024 |
Public URL | https://nottingham-repository.worktribe.com/output/31154253 |
Related Public URLs | https://nips.cc/virtual/2023/poster/72395 |
Additional Information | https://openreview.net/forum?id=D2cS6SoYlP |
You might also like
Relativistic Perturbation Theory for Black-Hole Boson Clouds
(2024)
Journal Article
Gravitational wave populations and cosmology with neural posterior estimation
(2024)
Journal Article
Downloadable Citations
About Repository@Nottingham
Administrator e-mail: discovery-access-systems@nottingham.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search