Papers

Simulation-based inference with scattering representations scattering is all you need

K Lin, B Joachimi, JD McEwen - arXiv preprint arXiv:2410.11883, 2024 - arxiv.org
Computer Science paper cs.LG Suggest

… We demonstrate the first successful use of scattering representations without further compression for simulation-based inference (SBI) with images (ie field-level), …

Cited by Link to paper

BibTeX

@article{2410.11883v3,
Author        = {Kiyam Lin and Benjamin Joachimi and Jason D. McEwen},
Title         = {Simulation-based inference with scattering representations: scattering
  is all you need},
Eprint        = {2410.11883v3},
ArchivePrefix = {arXiv},
PrimaryClass  = {cs.LG},
Abstract      = {We demonstrate the successful use of scattering representations without
further compression for simulation-based inference (SBI) with images (i.e.
field-level), illustrated with a cosmological case study. Scattering
representations provide a highly effective representational space for
subsequent learning tasks, although the higher dimensional compressed space
introduces challenges. We overcome these through spatial averaging, coupled
with more expressive density estimators. Compared to alternative methods, such
an approach does not require additional simulations for either training or
computing derivatives, is interpretable, and resilient to covariate shift. As
expected, we show that a scattering only approach extracts more information
than traditional second order summary statistics.},
Year          = {2024},
Month         = {Oct},
Url           = {http://arxiv.org/abs/2410.11883v3},
File          = {2410.11883v3.pdf}
}

Share