Denoising Diffusion Delensing Delight: Reconstructing the Non-Gaussian CMB Lensing Potential with Diffusion Models

TL;DR

This paper introduces a novel application of denoising diffusion models for Bayesian reconstruction of the non-Gaussian CMB lensing potential, surpassing traditional Gaussian assumptions and enabling more accurate cosmological analyses.

Contribution

It demonstrates the effectiveness of score-based generative models for non-Gaussian lensing reconstruction, moving beyond Gaussian assumptions and improving the accuracy of CMB lensing maps.

Findings

Diffusion models produce accurate, uncorrelated samples of the lensing potential.

The approach captures non-Gaussian statistics beyond the power spectrum.

Samples are validated against Hamiltonian Monte Carlo methods.

Abstract

Optimal extraction of cosmological information from observations of the Cosmic Microwave Background critically relies on our ability to accurately undo the distortions caused by weak gravitational lensing. In this work, we demonstrate the use of denoising diffusion models in performing Bayesian lensing reconstruction. We show that score-based generative models can produce accurate, uncorrelated samples from the CMB lensing convergence map posterior, given noisy CMB observations. To validate our approach, we compare the samples of our model to those obtained using established Hamiltonian Monte Carlo methods, which assume a Gaussian lensing potential. We then go beyond this assumption of Gaussianity, and train and validate our model on non-Gaussian lensing data, obtained by ray-tracing N-body simulations. We demonstrate that in this case, samples from our model have accurate non-Gaussian statistics beyond the power spectrum. The method provides an avenue towards more efficient and accurate lensing reconstruction, that does not rely on an approximate analytic description of the posterior probability. The reconstructed lensing maps can be used as an unbiased tracer of the matter distribution, and to improve delensing of the CMB, resulting in more precise cosmological parameter inference.