Replacing Gaussian Processes with Neural Networks in Pulsar Timing Array Inference of the Gravitational-Wave Background
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911730467078144 |
|---|---|
| author | Tiruvaskar, Shreyas Gordon, Chris |
| author_facet | Tiruvaskar, Shreyas Gordon, Chris |
| contents | Bayesian inference of nanohertz gravitational-wave background models in pulsar timing array analyses often relies on Gaussian-process interpolators to avoid repeated, computationally expensive strain-spectrum calculations. However, Gaussian-process training becomes a bottleneck for large training sets. We test whether probabilistic neural networks can replace Gaussian processes in this role for both a self-interacting dark matter model and a phenomenological environmental model. We find that neural networks recover consistent posteriors while significantly reducing both training and Markov chain Monte Carlo runtime, with the largest gains for the more computationally demanding model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_04340 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Replacing Gaussian Processes with Neural Networks in Pulsar Timing Array Inference of the Gravitational-Wave Background Tiruvaskar, Shreyas Gordon, Chris Cosmology and Nongalactic Astrophysics Data Analysis, Statistics and Probability Bayesian inference of nanohertz gravitational-wave background models in pulsar timing array analyses often relies on Gaussian-process interpolators to avoid repeated, computationally expensive strain-spectrum calculations. However, Gaussian-process training becomes a bottleneck for large training sets. We test whether probabilistic neural networks can replace Gaussian processes in this role for both a self-interacting dark matter model and a phenomenological environmental model. We find that neural networks recover consistent posteriors while significantly reducing both training and Markov chain Monte Carlo runtime, with the largest gains for the more computationally demanding model. |
| title | Replacing Gaussian Processes with Neural Networks in Pulsar Timing Array Inference of the Gravitational-Wave Background |
| topic | Cosmology and Nongalactic Astrophysics Data Analysis, Statistics and Probability |
| url | https://arxiv.org/abs/2604.04340 |