REVIEW 3 cited by
Hybrid Physical-Neural ODEs for Fast N-body Simulations
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We present a new scheme to compensate for the small-scales approximations resulting from Particle-Mesh (PM) schemes for cosmological N-body simulations. This kind of simulations are fast and low computational cost realizations of the large scale structures, but lack resolution on small scales. To improve their accuracy, we introduce an additional effective force within the differential equations of the simulation, parameterized by a Fourier-space Neural Network acting on the PM-estimated gravitational potential. We compare the results for the matter power spectrum obtained to the ones obtained by the PGD scheme (Potential gradient descent scheme). We notice a similar improvement in term of power spectrum, but we find that our approach outperforms PGD for the cross-correlation coefficients, and is more robust to changes in simulation settings (different resolutions, different cosmologies).
Forward citations
Cited by 3 Pith papers
-
DISCO-DJ II: a differentiable particle-mesh code for cosmology
A GPU-accelerated, differentiable particle-mesh N-body code achieves per-cent-level power-spectrum accuracy with few time steps and recovers sigma_8 plus initial conditions from a noisy mock field.
-
The Cosmological analysis of X-ray cluster surveys VII. Bypassing scaling relations with Lagrangian Deep Learning and Simulation-based inference
A simulation-based forward model combining conditioned Lagrangian Deep Learning with simulation-based inference aims to bypass empirical scaling relations in X-ray cluster cosmology, demonstrated on CAMELS/IllustrisTN...
-
Computing Nonlinear Power Spectra Across Dynamical Dark Energy Model Space with Neural ODEs
A neural ODE trained only on LambdaCDM spectra predicts nonlinear matter power spectra to about 4 percent accuracy for smooth w(z) dark energy models, pending stronger validation.
Discussion (0). Sign in to comment.