24–28 Aug 2026
Leiden University
Europe/Zurich timezone

From Few Simulations to Trustworthy Posteriors: Scattering-Covariance Latent Spaces for Simulation Augmentation and Interpretable SBI in CMB and Weak-Lensing Cosmology

Not scheduled
20m
Gorlaeus gebouw (Leiden University)

Gorlaeus gebouw

Leiden University

Einsteinweg 55, 2333 CC Leiden
Talk Cosmic Microwave Background

Speaker

Dr Paolo Campeti (Istituto Nazionale di Fisica Nucleare)

Description

Modern CMB and large-scale-structure analyses face some of the same statistical bottleneck: the data are high-dimensional, non-Gaussian, affected by complex systematics, and often have intractable likelihoods, while the end-to-end simulations needed for Monte Carlo validation or Simulation-Based Inference are prohibitively expensive. I will present a unified framework based on the Scattering Covariance: an interpretable, physics-informed analogue of a convolutional neural network, built from fixed oriented wavelets, nonlinearities, and cross-scale/cross-channel covariance statistics.

In recent work (Campeti et al., A&A, 2025), we used this representation to construct a fast map-level generative emulator for CMB instrumental systematics simulations. Even when trained on as few as ten high-fidelity simulations, the emulator generates statistically independent approximate realizations that reproduce power spectra, scattering statistics, Minkowski functionals, and pixel-covariance structure, enabling orders-of-magnitude simulation augmentation at negligible cost compared with full end-to-end campaigns.

I will then describe how the same scattering-covariance latent space can be used for transparent SBI pipelines: for CMB polarization, to infer parameters such as the optical depth to reionization and the tensor-to-scalar ratio while controlling non-stationary foreground and instrumental residuals; and for weak-lensing cosmology, to emulate high-resolution non-Gaussian convergence maps and infer parameters such as $\Omega_m$ and $\sigma_8$ beyond two-point statistics. The goal is a simulation-efficient, interpretable alternative to ``black-box'' neural inference: using a few expensive simulations as anchors for large, calibrated, statistically-controlled inference pipelines.

Other topic / keywords: Weak Lensing, Simulation-Based Inference

Author

Dr Paolo Campeti (Istituto Nazionale di Fisica Nucleare)

Co-authors

Prof. Erwan Allys (Laboratoire de Physique de l’Ecole Normale Supérieure, ENS) Dr Jean-Marc Delouis (Laboratoire d’Océanographie Physique et Spatiale (LOPS), Univ. Brest, CNRS, Ifremer) Prof. Luca Pagano (INFN, University of Ferrara) Dr Martina Gerbino (Istituto Nazionale di Fisica Nucleare) Dr Massimiliano Lattanzi (Istituto Nazionale di Fisica Nucleare)

Presentation materials

There are no materials yet.