A Fast Generative Framework for High-dimensional Posterior Sampling: Application to CMB Delensing

• URL: http://arxiv.org/abs/2603.04535v1
• Date: Wed, 04 Mar 2026 19:21:59 GMT
• Title: A Fast Generative Framework for High-dimensional Posterior Sampling: Application to CMB Delensing
• Abstract summary: We introduce a deep generative framework for high-dimensional Bayesian inference that enables efficient posterior sampling.<n>Our method performs posterior sampling an order of magnitude faster than a diffusion baseline.<n>It successfully recovers the unlensed CMB power spectrum from simulated observations.
• Score: 5.827948146001617
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce a deep generative framework for high-dimensional Bayesian inference that enables efficient posterior sampling. As telescopes and simulations rapidly expand the volume and resolution of astrophysical data, fast simulation-based inference methods are increasingly needed to extract scientific insights. While diffusion-based approaches offer high-quality generative capabilities, they are hindered by slow sampling speeds. Our method performs posterior sampling an order of magnitude faster than a diffusion baseline. Applied to the problem of CMB delensing, it successfully recovers the unlensed CMB power spectrum from simulated observations. The model also remains robust to shifts in cosmological parameters, demonstrating its potential for out-of-distribution generalization and application to observational cosmological data.

Related papers

• Strong Gravitational Lensing Posterior Sampling in Pixel-Space Using Diffusion Models and Recurrent Inference Machines [4.7414910806409996]
  We present a method to generate posterior samples of the source galaxy and foreground mass distribution as pixelated images conditioned on observations.<n>It can model realistic gravitational lensing simulations with background and foreground galaxies drawn from cosmological hydrodynamical simulations down to the noise level.
  arXiv  Detail & Related papers  (2026-07-21T18:00:00Z)
• Provable Maximum Entropy Manifold Exploration via Diffusion Models [58.89696361871563]
  Exploration is critical for solving real-world decision-making problems such as scientific discovery.<n>We introduce a novel framework that casts exploration as entropy over approximate data manifold implicitly defined by a pre-trained diffusion model.<n>We develop an algorithm based on mirror descent that solves the exploration problem as sequential fine-tuning of a pre-trained diffusion model.
  arXiv  Detail & Related papers  (2025-06-18T11:59:15Z)
• Fast Sampling of Cosmological Initial Conditions with Gaussian Neural Posterior Estimation [4.520518890664213]
  We show how simulation-based inference can be used to obtain data-constrained realisations of the primordial dark matter density field.<n>We generate thousands of posterior samples within seconds on a single GPU, orders of magnitude faster than existing methods.
  arXiv  Detail & Related papers  (2025-02-05T13:02:14Z)
• Arbitrary-steps Image Super-resolution via Diffusion Inversion [68.78628844966019]
  This study presents a new image super-resolution (SR) technique based on diffusion inversion, aiming at harnessing the rich image priors encapsulated in large pre-trained diffusion models to improve SR performance.<n>We design a Partial noise Prediction strategy to construct an intermediate state of the diffusion model, which serves as the starting sampling point.<n>Once trained, this noise predictor can be used to initialize the sampling process partially along the diffusion trajectory, generating the desirable high-resolution result.
  arXiv  Detail & Related papers  (2024-12-12T07:24:13Z)
• Parallel Simulation for Log-concave Sampling and Score-based Diffusion Models [55.07411490538404]
  We propose a novel parallel sampling method that improves adaptive complexity dependence on dimension $d$.<n>Our approach builds on parallel simulation techniques from scientific computing.
  arXiv  Detail & Related papers  (2024-12-10T11:50:46Z)
• Bayesian Deconvolution of Astronomical Images with Diffusion Models: Quantifying Prior-Driven Features in Reconstructions [40.13294159814764]
  Deconvolution of astronomical images is a key aspect of recovering the intrinsic properties of celestial objects.<n>This paper explores the use of diffusion models (DMs) and the Diffusion Posterior Sampling (DPS) algorithm to solve this inverse problem task.
  arXiv  Detail & Related papers  (2024-11-28T14:00:00Z)
• Diffusion posterior sampling for simulation-based inference in tall data settings [53.17563688225137]
  Simulation-based inference ( SBI) is capable of approximating the posterior distribution that relates input parameters to a given observation. In this work, we consider a tall data extension in which multiple observations are available to better infer the parameters of the model. We compare our method to recently proposed competing approaches on various numerical experiments and demonstrate its superiority in terms of numerical stability and computational cost.
  arXiv  Detail & Related papers  (2024-04-11T09:23:36Z)
• Multi-Modal Learning-based Reconstruction of High-Resolution Spatial Wind Speed Fields [46.72819846541652]
  We propose a framework based on Vari Data Assimilation and Deep Learning concepts. This framework is applied to recover rich-in-time, high-resolution information on sea surface wind speed.
  arXiv  Detail & Related papers  (2023-12-14T13:40:39Z)
• Inferring Atmospheric Properties of Exoplanets with Flow Matching and Neural Importance Sampling [10.847353970405285]
  Atmospheric retrievals characterize exoplanets by estimating atmospheric parameters from observed light spectra. Traditional approaches such as nested sampling are computationally expensive, sparking an interest in solutions based on machine learning (ML) We first explore flow matching posterior estimation (FMPE) as a new ML-based method for AR and find that, in our case, it is more accurate than neural posterior estimation (NPE) We then combine both FMPE and NPE with importance sampling, in which case both methods outperform nested sampling in terms of accuracy and simulation efficiency.
  arXiv  Detail & Related papers  (2023-12-13T17:12:03Z)
• DiffuSeq-v2: Bridging Discrete and Continuous Text Spaces for Accelerated Seq2Seq Diffusion Models [58.450152413700586]
  We introduce a soft absorbing state that facilitates the diffusion model in learning to reconstruct discrete mutations based on the underlying Gaussian space. We employ state-of-the-art ODE solvers within the continuous space to expedite the sampling process. Our proposed method effectively accelerates the training convergence by 4x and generates samples of similar quality 800x faster.
  arXiv  Detail & Related papers  (2023-10-09T15:29:10Z)
• Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems [64.29491112653905]
  We propose a novel and efficient diffusion sampling strategy that synergistically combines the diffusion sampling and Krylov subspace methods. Specifically, we prove that if tangent space at a denoised sample by Tweedie's formula forms a Krylov subspace, then the CG with the denoised data ensures the data consistency update to remain in the tangent space. Our proposed method achieves more than 80 times faster inference time than the previous state-of-the-art method.
  arXiv  Detail & Related papers  (2023-03-10T07:42:49Z)
• Neural Posterior Estimation with Differentiable Simulators [58.720142291102135]
  We present a new method to perform Neural Posterior Estimation (NPE) with a differentiable simulator. We demonstrate how gradient information helps constrain the shape of the posterior and improves sample-efficiency.
  arXiv  Detail & Related papers  (2022-07-12T16:08:04Z)
• Provable RL with Exogenous Distractors via Multistep Inverse Dynamics [85.52408288789164]
  Real-world applications of reinforcement learning (RL) require the agent to deal with high-dimensional observations such as those generated from a megapixel camera. Prior work has addressed such problems with representation learning, through which the agent can provably extract endogenous, latent state information from raw observations. However, such approaches can fail in the presence of temporally correlated noise in the observations.
  arXiv  Detail & Related papers  (2021-10-17T15:21:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.