An official website of the United States government
Abstract Galaxies are biased tracers of the underlying cosmic web, which is dominated by dark matter (DM) components that cannot be directly observed. Galaxy formation simulations can be used to study the relationship between DM density fields and galaxy distributions. However, this relationship can be sensitive to assumptions in cosmology and astrophysical processes embedded in galaxy formation models, which remain uncertain in many aspects. In this work, we develop a diffusion generative model to reconstruct DM fields from galaxies. The diffusion model is trained on the CAMELS simulation suite that contains thousands of state-of-the-art galaxy formation simulations with varying cosmological parameters and subgrid astrophysics. We demonstrate that the diffusion model can predict the unbiased posterior distribution of the underlying DM fields from the given stellar density fields while being able to marginalize over uncertainties in cosmological and astrophysical models. Interestingly, the model generalizes to simulation volumes ≈500 times larger than those it was trained on and across different galaxy formation models. The code for reproducing these results can be found athttps://github.com/victoriaono/variational-diffusion-cdm✎.
more »
« less
Diffusion-HMC: Parameter Inference with Diffusion-model-driven Hamiltonian Monte Carlo
Abstract Diffusion generative models have excelled at diverse image generation and reconstruction tasks across fields. A less explored avenue is their application to discriminative tasks involving regression or classification problems. The cornerstone of modern cosmology is the ability to generate predictions for observed astrophysical fields from theory and constrain physical models from observations using these predictions. This work uses a single diffusion generative model to address these interlinked objectives—as a surrogate model or emulator for cold dark matter density fields conditional on input cosmological parameters, and as a parameter inference model that solves the inverse problem of constraining the cosmological parameters of an input field. The model is able to emulate fields with summary statistics consistent with those of the simulated target distribution. We then leverage the approximate likelihood of the diffusion generative model to derive tight constraints on cosmology by using the Hamiltonian Monte Carlo method to sample the posterior on cosmological parameters for a given test image. Finally, we demonstrate that this parameter inference approach is more robust to small perturbations of noise to the field than baseline parameter inference networks.
more »
« less
- Award ID(s):
- 2019786
- PAR ID:
- 10570061
- Publisher / Repository:
- The American Astronomical Society
- Date Published:
- Journal Name:
- The Astrophysical Journal
- Volume:
- 978
- Issue:
- 1
- ISSN:
- 0004-637X
- Page Range / eLocation ID:
- 64
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
We present Prompt Diffusion, a framework for enabling in-context learning in diffusion-based generative models. Given a pair of task-specific example images, such as depth from/to image and scribble from/to image, and a text guidance, our model automatically understands the underlying task and performs the same task on a new query image following the text guidance. To achieve this, we propose a vision-language prompt that can model a wide range of vision-language tasks and a diffusion model that takes it as input. The diffusion model is trained jointly on six different tasks using these prompts. The resulting Prompt Diffusion model becomes the first diffusion-based vision-language foundation model capable of in-context learning. It demonstrates high-quality in-context generation for the trained tasks and effectively generalizes to new, unseen vision tasks using their respective prompts. Our model also shows compelling text-guided image editing results. Our framework aims to facilitate research into in-context learning for computer vision. We share our code and pre-trained models at https://github. com/Zhendong-Wang/Prompt-Diffusion.more » « less
-
ABSTRACT We present a coherent, re-usable python framework building on the CosmoPower emulator code for high-accuracy calculations of cosmological observables with Einstein–Boltzmann codes. For detailed statistical analyses, such codes require high computing power, making parameter space exploration costly, especially for beyond-$$\Lambda$$CDM analyses. Machine learning-enabled emulators of Einstein–Boltzmann codes are becoming an increasingly popular solution to this problem. To enable generation, sharing, and use of emulators for inference, we define standards for robustly describing, packaging, and distributing them. We present software for easily performing these tasks in an automated and replicable manner and provide examples and guidelines for generating emulators and wrappers for using them in popular cosmological inference codes. We demonstrate our framework with a suite of high-accuracy emulators for the CAMB code’s calculations of CMB $$C_\ell$$, $P(k)$, background evolution, and derived parameter quantities. We show these emulators are accurate enough for analysing both $$\Lambda$$CDM and a set of extension models ($$N_{\rm eff}$$, $$\sum m_\nu$$, $$w_0 w_a$$) with stage-IV observatories, recovering the original high-accuracy spectra to tolerances well within the cosmic variance uncertainties. We show our emulators also recover cosmological parameters in a simulated cosmic-variance limited experiment, finding results well within $$0.1 \sigma$$ of the input cosmology, while requiring $$\lesssim 1/50$$ of the evaluation time.more » « less
-
Diffusion models are vulnerable to backdoor attacks, where malicious attackers inject backdoors by poisoning certain training samples during the training stage. This poses a significant threat to real-world applications in the Model-as-a-Service (MaaS) scenario, where users query diffusion models through APIs or directly download them from the internet. To mitigate the threat of backdoor attacks under MaaS, black-box input-level backdoor detection has drawn recent interest, where defenders aim to build a firewall that filters out backdoor samples in the inference stage, with access only to input queries and the generated results from diffusion models. Despite some preliminary explorations on the traditional classification tasks, these methods cannot be directly applied to the generative tasks due to two major challenges: (1) more diverse failures and (2) a multi-modality attack surface. In this paper, we propose a black-box input-level backdoor detection framework on diffusion models, called UFID. Our defense is motivated by an insightful causal analysis: Backdoor attacks serve as the confounder, introducing a spurious path from input to target images, which remains consistent even when we perturb the input samples with Gaussian noise. We further validate the intuition with theoretical analysis. Extensive experiments across different datasets on both conditional and unconditional diffusion models show that our method achieves superb performance on detection effectiveness and run-time efficiency.more » « less
-
Standard diffusion models involve an image transform -- adding Gaussian noise -- and an image restoration operator that inverts this degradation. We observe that the generative behavior of diffusion models is not strongly dependent on the choice of image degradation, and in fact, an entire family of generative models can be constructed by varying this choice. Even when using completely deterministic degradations (e.g., blur, masking, and more), the training and test-time update rules that underlie diffusion models can be easily generalized to create generative models. The success of these fully deterministic models calls into question the community's understanding of diffusion models, which relies on noise in either gradient Langevin dynamics or variational inference and paves the way for generalized diffusion models that invert arbitrary processes.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Journal Article:
- https://doi.org/10.3847/1538-4357/ad8bc3
