Simulation-Efficient Cosmological Inference with Multi-Fidelity SBI

Leander Thiele, Adrian E. Bayer, Naoya Takeishi
7/1/2025
astro-ph.COcs.LG

No confident code implementation found for this paper.

Abstract

The simulation cost for cosmological simulation-based inference can be decreased by combining simulation sets of varying fidelity. We propose an approach to such multi-fidelity inference based on feature matching and knowledge distillation. Our method results in improved posterior quality, particularly for small simulation budgets and difficult inference problems.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Simulation-based stacking

82% match2023

Dynamic SBI: Round-free Sequential Simulation-Based Inference with Adaptive Datasets

81% match2025

Simulation-Based Inference: A Practical Guide

80% match1 repo272025

Multifidelity Simulation-based Inference for Computationally Expensive Simulators

80% match1 repo52025

Multilevel neural simulation-based inference

78% match1 repo12025

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

78% match2026

Cite this paper

@article{thiele2025simulationefficient,
  title  = {Simulation-Efficient Cosmological Inference with Multi-Fidelity SBI},
  author = {Leander Thiele and Adrian E. Bayer and Naoya Takeishi},
  year   = {2025},
  eprint = {2507.00514},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2507.00514v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2507.00514.svg)](https://codeofpaper.com/paper/2507.00514)

Discussion