Simulation based inference with domain adaptation for strong gravitational lensing
- Fermilab
Simulation based inference leverages machine learning to carry out Bayesian inference in systems with intractable likelihoods. However, transitioning a network trained on simulated data to real data runs the risk of encountering domain shift, leading to performance losses. We attempt to implement domain adaptation into the sbi neural posterior estimation framework using the Maximum Mean Discrepancy as an additional network loss, using masked autoregressive fow (MAF) as our density estimator. We test the network on a set of 400,000 simulated strong gravitational lensing images generated using deeplenstronomy. The source domain is defined as low noise whereas the target domain has a noise profile sampled from experimentally derived DES survey conditions. We find that SBI appears robust against small changes in the data with similar performance on source and target. Moreover, while DA does lead to performance improvements, they are marginal at 6% less inference error.
- Research Organization:
- Fermi National Accelerator Laboratory (FNAL), Batavia, IL (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC), High Energy Physics (HEP)
- DOE Contract Number:
- AC02-07CH11359
- OSTI ID:
- 2246748
- Report Number(s):
- FERMILAB-PUB-23-796-STUDENT; oai:inspirehep.net:2731283
- Journal Information:
- TBD, Journal Name: TBD
- Country of Publication:
- United States
- Language:
- English
Similar Records
Domain-Adaptive Neural Posterior Estimation for Strong Gravitational Lens Analysis
Deep inference of simulated strong lenses in ground-based surveys