On simulated weak lensing maps, the Neural Field Scattering Transform with trained filters improves constraints on sigma_8 and w by 6-11% and posterior density by about 17% over the standard Wavelet Scattering Transform.
We use the same MLP model and training setup as with pre-training, but in- stead train for 2000 epochs with a learning rate of 10−4
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
astro-ph.CO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Balanced Field Summaries of the Large-Scale Structure with the Neural Field Scattering Transform
On simulated weak lensing maps, the Neural Field Scattering Transform with trained filters improves constraints on sigma_8 and w by 6-11% and posterior density by about 17% over the standard Wavelet Scattering Transform.