COmoving Computer Acceleration (COCA): $N$-body simulations in an emulated frame of reference

Abstract

$N$-body simulations are computationally expensive, so machine-learning (ML)-based emulation techniques have emerged as a way to increase their speed. Although fast, surrogate models have limited trustworthiness due to potentially substantial emulation errors that current approaches cannot correct for. To alleviate this problem, we introduce COmoving Computer Acceleration (COCA), a hybrid framework interfacing ML with an $N$-body simulator. The correct physical equations of motion are solved in an emulated frame of reference, so that any emulation error is corrected by design. This approach corresponds to solving for the perturbation of particle trajectories around the machine-learnt solution, which is computationally cheaper than obtaining the full solution, yet is guaranteed to converge to the truth as one increases the number of force evaluations. Although applicable to any ML algorithm and $N$-body simulator, this approach is assessed in the particular case of particle-mesh cosmological simulations in a frame of reference predicted by a convolutional neural network, where the time dependence is encoded as an additional input parameter to the network. COCA efficiently reduces emulation errors in particle trajectories, requiring far fewer force evaluations than running the corresponding simulation without ML. We obtain accurate final density and velocity fields for a reduced computational budget. We demonstrate that this method shows robustness when applied to examples outside the range of the training data. When compared to the direct emulation of the Lagrangian displacement field using the same training resources, COCA's ability to correct emulation errors results in more accurate predictions. COCA makes $N$-body simulations cheaper by skipping unnecessary force evaluations, while still solving the correct equations of motion and correcting for emulation errors made by ML.

23 pages, 13 figures. Accepted for publication in A&A

References in corpus (38)

• Large-Scale Structure of the Universe and Cosmological Perturbation Theory
• Solving Large Scale Structure in Ten Easy Steps with COLA
• The Uchuu Simulations: Data Release 1 and Dark Matter Halo Concentrations
• Learning to Predict the Cosmological Structure Formation
• FastPM: a new scheme for fast simulations of dark matter and halos
• Large-scale dark matter simulations
• ELUCID - Exploring the Local Universe with reConstructed Initial Density field I: Hamiltonian Markov Chain Monte Carlo Method with Particle Mesh Dynamics
• Physical Bayesian modelling of the non-linear matter distribution: new insights into the Nearby Universe
• The Properties of Cosmic Velocity Fields
• Nuisance hardened data compression for fast likelihood-free inference
• The Outer Rim Simulation: A Path to Many-Core Supercomputers
• ICE-COLA: Towards fast and accurate synthetic galaxy catalogues optimizing a quasi $N$-body method
• AI-assisted super-resolution cosmological simulations
• Fast and accurate mock catalogue generation for low-mass galaxies
• Bayesian optimisation for likelihood-free cosmological inference
• Super-resolution emulator of cosmological simulations using deep physical models
• Machine learning cosmological structure formation
• Bayesian analysis of the dynamic cosmic web in the SDSS galaxy survey
• COLA with massive neutrinos
• CARPool: fast, accurate computation of large-scale structure statistics by pairing costly and cheap cosmological simulations
• FlowPM: Distributed TensorFlow Implementation of the FastPM Cosmological N-body Solver
• Field Level Neural Network Emulator for Cosmological N-body Simulations
• Learning effective physical laws for generating cosmological hydrodynamics with Lagrangian Deep Learning
• Preparing for the Cosmic Shear Data Flood: Optimal Data Extraction and Simulation Requirements for Stage IV Dark Energy Experiments
• LtU-ILI: An All-in-One Framework for Implicit Inference in Astrophysics and Cosmology
• The phase-space structure of nearby dark matter as constrained by the SDSS
• Estimating CDM Particle Trajectories in the Mildly Non-Linear Regime of Structure Formation. Implications for the Density Field in Real and Redshift Space
• Bayesian Inference of Initial Conditions from Non-Linear Cosmic Structures using Field-Level Emulators
• Primordial power spectrum and cosmology from black-box galaxy surveys
• Farpoint: A High-Resolution Cosmology Simulation at the Gigaparsec Scale
• Perfectly parallel cosmological simulations using spatial comoving Lagrangian acceleration
• Constrained cosmological simulations of the Local Group using Bayesian hierarchical field-level inference
• Learning neutrino effects in Cosmology with Convolutional Neural Networks
• The Ultramarine Simulation: properties of dark matter haloes before redshift 5.5
• $\text{PineTree}$: A generative, fast, and differentiable halo model for wide-field galaxy surveys
• Simple lessons from complex learning: what a neural network model learns about cosmic structure formation
• A field-level emulator for modified gravity
• Perturbation-theory informed integrators for cosmological simulations

Cited by in corpus (4)

• BullFrog: Multi-step perturbation theory as a time integrator for cosmological simulations
• Learning the Universe: Learning to Optimize Cosmic Initial Conditions with Non-Differentiable Structure Formation Models
• Towards an optimal extraction of cosmological parameters from galaxy cluster surveys using convolutional neural networks
• Predicting large scale cosmological structure evolution with generative adversarial network-based autoencoders