FastPM: Fast Pretrained Model for Cosmological Simulation-Based Inference
Abstract
Modern cosmology increasingly relies on large ensembles of expensive simulations to model the non-linear Universe and extract information from upcoming surveys. However, generating high-fidelity simulations---whether gravity-only N-body or full hydrodynamical---requires substantial computational resources. In this work, we demonstrate that transfer learning from fast low-fidelity simulations can dramatically reduce the cost of training machine learning models, in particular for simulation-based inference (SBI). We train a Fast Pretrained Model (FastPM) on a set of Fast Particle-Mesh (FastPM) simulations to infer Ωm and σ8 from the power spectrum, and finetune on a smaller set of high-fidelity CAMELS N-body and hydrodynamical simulations. To reach a fixed posterior accuracy, the pretrained model requires only 5--15\% of the high-fidelity simulations compared to the number of simulations needed when training on CAMELS alone, reducing the total training simulation compute cost, including that of the pretraining simulations, by up to an order of magnitude in CPU hours. Remarkably, the gains persist for the total matter power spectrum of full hydrodynamical simulations: although FastPM contains no baryonic physics, pretraining on FastPM runs that together cost less than a single hydrodynamical simulation still reduces the total training simulation compute by a factor of ∼5. Moreover, pretraining on more accurate FastPM runs yields more accurate posteriors than training on CAMELS alone achieves with any number of simulations we consider. These results demonstrate that transfer learning from fast simulations is a simple and powerful route to high-fidelity SBI, and highlight the promise of simulation-based foundation models in cosmology.
Related
- VROOM-SBI: A Fast Simulation-Based Bayesian Inference Methodology for Stokes QU-Fitting in Radio Interferometry
- Merlin: Fast and flexible 3x2pt cosmology with simulation-based inference
- Type Ia supernova population machine – I. A unified cosmological simulation–binary synthesis framework establishing non-universal delay-time distributions and cosmic progenitor-channel dominance crossover
- Bridging perturbation theory and simulations: initial conditions and fast integrators for cosmological simulations
- Dark Energy Constraints and Joint Cosmological Inference from Mutually Inconsistent Observations
BibTeX
@misc{yamamoto2026fastpm,
title = {{FastPM: Fast Pretrained Model for Cosmological Simulation-Based Inference}},
author = {Masaya Yamamoto and Adrian E. Bayer},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.33955},
eprint = {2610.33955},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.33955},
}
RIS
TY - UNPB
TI - FastPM: Fast Pretrained Model for Cosmological Simulation-Based Inference
AU - Masaya Yamamoto
AU - Adrian E. Bayer
PY - 2026
DA - 2026/10/24
PB - arXiv
DO - 10.48550/arxiv.2610.33955
UR - https://arxiv.org/abs/2610.33955
AB - Modern cosmology increasingly relies on large ensembles of expensive simulations to model the non-linear Universe and extract information from upcoming surveys. However, generating high-fidelity simulations---whether gravity-only N-body or full hydrodynamical---requires substantial computational resources. In this work, we demonstrate that transfer learning from fast low-fidelity simulations can dramatically reduce the cost of training machine learning models, in particular for simulation-based inference (SBI). We train a Fast Pretrained Model (FastPM) on a set of Fast Particle-Mesh (FastPM) simulations to infer Ω_m and σ_8 from the power spectrum, and finetune on a smaller set of high-fidelity CAMELS N-body and hydrodynamical simulations. To reach a fixed posterior accuracy, the pretrained model requires only 5--15\% of the high-fidelity simulations compared to the number of simulations needed when training on CAMELS alone, reducing the total training simulation compute cost, including that of the pretraining simulations, by up to an order of magnitude in CPU hours. Remarkably, the gains persist for the total matter power spectrum of full hydrodynamical simulations: although FastPM contains no baryonic physics, pretraining on FastPM runs that together cost less than a single hydrodynamical simulation still reduces the total training simulation compute by a factor of ∼5. Moreover, pretraining on more accurate FastPM runs yields more accurate posteriors than training on CAMELS alone achieves with any number of simulations we consider. These results demonstrate that transfer learning from fast simulations is a simple and powerful route to high-fidelity SBI, and highlight the promise of simulation-based foundation models in cosmology.
ER -