Machine Learning Techniques for Astrophysics and Cosmology: Simulation-Based Inference
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916001118945280 |
|---|---|
| author | Thiele, Leander |
| author_facet | Thiele, Leander |
| contents | Simulation-based inference (SBI) enables parameter inference by training neural networks on forward simulations. It is being applied both for intractable likelihoods as well as under time constraints on the posterior sampling. After motivating situations in which SBI is useful, we give a pedagogical description of the basic techniques. These are posterior, likelihood, and ratio estimation. Alternatives, sequential versions, and learned summaries are discussed briefly. We provide a brief guide to choosing among the techniques in practical scenarios. SBI needs to be verified through diagnostics since failures can be subtle but would invalidate the inference result. We explain the most common diagnostic techniques. We briefly list some recent SBI applications in the cosmology and astrophysics literature. Before concluding, we discuss current methodological challenges. We identify training with limited simulation budgets as the critical problem for applications to cosmology and astrophysics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_10719 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Machine Learning Techniques for Astrophysics and Cosmology: Simulation-Based Inference Thiele, Leander Cosmology and Nongalactic Astrophysics Instrumentation and Methods for Astrophysics Simulation-based inference (SBI) enables parameter inference by training neural networks on forward simulations. It is being applied both for intractable likelihoods as well as under time constraints on the posterior sampling. After motivating situations in which SBI is useful, we give a pedagogical description of the basic techniques. These are posterior, likelihood, and ratio estimation. Alternatives, sequential versions, and learned summaries are discussed briefly. We provide a brief guide to choosing among the techniques in practical scenarios. SBI needs to be verified through diagnostics since failures can be subtle but would invalidate the inference result. We explain the most common diagnostic techniques. We briefly list some recent SBI applications in the cosmology and astrophysics literature. Before concluding, we discuss current methodological challenges. We identify training with limited simulation budgets as the critical problem for applications to cosmology and astrophysics. |
| title | Machine Learning Techniques for Astrophysics and Cosmology: Simulation-Based Inference |
| topic | Cosmology and Nongalactic Astrophysics Instrumentation and Methods for Astrophysics |
| url | https://arxiv.org/abs/2605.10719 |