Cosmological Field Emulation and Parameter Inference with Diffusion Models (2312.07534v1)
Abstract: Cosmological simulations play a crucial role in elucidating the effect of physical parameters on the statistics of fields and on constraining parameters given information on density fields. We leverage diffusion generative models to address two tasks of importance to cosmology -- as an emulator for cold dark matter density fields conditional on input cosmological parameters $\Omega_m$ and $\sigma_8$, and as a parameter inference model that can return constraints on the cosmological parameters of an input field. We show that the model is able to generate fields with power spectra that are consistent with those of the simulated target distribution, and capture the subtle effect of each parameter on modulations in the power spectrum. We additionally explore their utility as parameter inference models and find that we can obtain tight constraints on cosmological parameters.
- The Coyote Universe II: Cosmological Models and Precision Emulation of the Nonlinear Matter Power Spectrum. Astrophys. J., 705:156–174, 2009. doi: 10.1088/0004-637X/705/1/156.
- Cosmogan: creating high-fidelity weak lensing convergence maps using generative adversarial networks. Computational Astrophysics and Cosmology, 6(1):1–13, 2019.
- Going beyond the galaxy power spectrum: An analysis of boss data with wavelet scattering transforms. Physical Review D, 106(10):103509, 2022.
- Multiscale flow for robust and optimal cosmological analysis. arXiv preprint arXiv:2306.04689, 2023.
- Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456, 2020.
- Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, 33:6840–6851, 2020.
- The illustristng simulations: public data release. Computational Astrophysics and Cosmology, 6(1):1–29, 2019.
- Simulating galaxy formation with the illustristng model. Monthly Notices of the Royal Astronomical Society, 473(3):4077–4106, 2018.
- The camels multifield data set: Learning the universe’s fundamental parameters with artificial intelligence. The Astrophysical Journal Supplement Series, 259(2):61, 2022.
- The camels project: Cosmology and astrophysics with machine-learning simulations. The Astrophysical Journal, 915(1):71, 2021a.
- U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234–241. Springer, 2015.
- Wide residual networks. arXiv preprint arXiv:1605.07146, 2016.
- Group normalization. In Proceedings of the European conference on computer vision (ECCV), pages 3–19, 2018.
- Attention is all you need. Advances in neural information processing systems, 30, 2017.
- Efficient attention: Attention with linear complexities. In Proceedings of the IEEE/CVF winter conference on applications of computer vision, pages 3531–3539, 2021.
- Lukas Biewald. Experiment tracking with weights and biases, 2020. URL https://www.wandb.com/. Software available from wandb.com.
- A note on the evaluation of generative models. arXiv preprint arXiv:1511.01844, 2015.
- Multifield cosmology with artificial intelligence. arXiv preprint arXiv:2109.09747, 2021b.
- Understanding the diffusion objective as a weighted integral of elbos. arXiv preprint arXiv:2303.00848, 2023.
- Likelihood-free mcmc with amortized approximate ratio estimators. In International conference on machine learning, pages 4239–4248. PMLR, 2020.