We propose a new field-level emulator that bridges two simulators using unpaired simulation datasets. Our method leverages a flow-based approach to learn the likelihood transport from one simulator to the other. Since multiple transport maps exist, we employ Conditional Optimal Transport Flow Matching (COT-FM) to ensure that the transformation minimally distorts the underlying structure of the data. We demonstrate the effectiveness of this approach by bridging weak lensing simulators: a Lagrangian Perturbation Theory (LPT) to a N-body Particle-Mesh (PM). We demonstrate that our emulator captures the full correction between the simulators by showing that it enables full-field inference to accurately recover the true posterior, validating its accuracy beyond traditional summary statistics.
@article{arxiv.2510.24631,
title = {Bridging Simulators with Conditional Optimal Transport},
author = {Justine Zeghal and Benjamin Remy and Yashar Hezaveh and Francois Lanusse and Laurence Perreault Levasseur},
journal= {arXiv preprint arXiv:2510.24631},
year = {2025}
}
Comments
Accepted at the 2025 Workshop on Machine Learning for Astrophysics, 10 pages, 6 figures