Posterior Sampling of the Initial Conditions of the Universe from Non-linear Large Scale Structures using Score-Based Generative Models

TL;DR

This paper introduces a novel score-based generative modeling approach to efficiently sample initial universe conditions from present-day observations, outperforming traditional simulation-based methods in speed and plausibility.

Contribution

It applies score-based generative models to cosmological initial condition inference, enabling fast, accurate sampling of early universe states from current data.

Findings

Samples match ground truth based on summary statistics

Method is significantly faster than existing approaches

Produces plausible realizations of early universe density fields

Abstract

Reconstructing the initial conditions of the universe is a key problem in cosmology. Methods based on simulating the forward evolution of the universe have provided a way to infer initial conditions consistent with present-day observations. However, due to the high complexity of the inference problem, these methods either fail to sample a distribution of possible initial density fields or require significant approximations in the simulation model to be tractable, potentially leading to biased results. In this work, we propose the use of score-based generative models to sample realizations of the early universe given present-day observations. We infer the initial density field of full high-resolution dark matter N-body simulations from the present-day density field and verify the quality of produced samples compared to the ground truth based on summary statistics. The proposed method is capable of providing plausible realizations of the early universe density field from the initial conditions posterior distribution marginalized over cosmological parameters and can sample orders of magnitude faster than current state-of-the-art methods.