LINNA: Likelihood Inference Neural Network Accelerator

Abstract

Bayesian posterior inference of modern multi-probe cosmological analyses incurs massive computational costs. For instance, depending on the combinations of probes, a single posterior inference for the Dark Energy Survey (DES) data had a wall-clock time that ranged from 1 to 21 days using a state-of-the-art computing cluster with 100 cores. These computational costs have severe environmental impacts and the long wall-clock time slows scientific productivity. To address these difficulties, we introduce LINNA: the Likelihood Inference Neural Network Accelerator. Relative to the baseline DES analyses, LINNA reduces the computational cost associated with posterior inference by a factor of 8--50. If applied to the first-year cosmological analysis of Rubin Observatory's Legacy Survey of Space and Time (LSST Y1), we conservatively estimate that LINNA will save more than US $\$300,000$ on energy costs, while simultaneously reducing ${\mathrm{CO}}_2$ emission by $2,400$ tons. To accomplish these reductions, LINNA automatically builds training data sets, creates neural network surrogate models, and produces a Markov chain that samples the posterior. We explicitly verify that LINNA accurately reproduces the first-year DES (DES Y1) cosmological constraints derived from a variety of different data vectors with our default code settings, without needing to retune the algorithm every time. Further, we find that LINNA is sufficient for enabling accurate and efficient sampling for LSST Y10 multi-probe analyses. We make LINNA publicly available at https://github.com/chto/linna, to enable others to perform fast and accurate posterior inference in contemporary cosmological analyses.

arXiv comment21 pages, 12 figures, submitted to JCAP, comments are welcome

References in corpus (29)

• emcee: The MCMC Hammer
• The NumPy array: a structure for efficient numerical computation
• MultiNest: an efficient and robust Bayesian inference tool for cosmology and particle physics
• Dark Energy Survey Year 1 Results: Cosmological Constraints from Galaxy Clustering and Weak Lensing
• Dark Energy Survey Year 3 Results: Cosmological Constraints from Galaxy Clustering and Weak Lensing
• Cluster Cosmology Constraints from the 2500 deg${}^2$ SPT-SZ Survey: Inclusion of Weak Gravitational Lensing Data from Magellan and the Hubble Space Telescope
• KiDS-450 + 2dFLenS: Cosmological parameter constraints from weak gravitational lensing tomography and overlapping redshift-space galaxy clustering
• CosmoLike - Cosmological Likelihood Analyses for Photometric Galaxy Surveys
• KiDS+GAMA: Cosmology constraints from a joint analysis of cosmic shear, galaxy-galaxy lensing and angular clustering
• Dark Energy Survey Year 1 Results: Weak Lensing Mass Calibration of redMaPPer Galaxy Clusters
• Fast likelihood-free cosmology with neural density estimators and active learning
• COSMOPOWER: emulating cosmological power spectra for accelerated Bayesian inference from next-generation surveys
• Euclid preparation: IX. EuclidEmulator2 -- Power spectrum emulation with massive neutrinos and self-consistent dark energy perturbations
• Massive optimal data compression and density estimation for scalable, likelihood-free inference in cosmology
• The Aemulus Project I: Numerical Simulations for Precision Cosmology
• Dark Energy Survey Year 1 Results: Cosmological Constraints from Cluster Abundances, Weak Lensing, and Galaxy Correlations
• The LSST Dark Energy Science Collaboration (DESC) Science Requirements Document
• Fast cosmological parameter estimation using neural networks
• Cosmological Reconstruction From Galaxy Light: Neural Network Based Light-Matter Connection
• Bayesian optimisation for likelihood-free cosmological inference
• zeus: A Python implementation of Ensemble Slice Sampling for efficient Bayesian parameter inference
• {\sc CosmoNet}: fast cosmological parameter estimation in non-flat models using neural networks
• PkANN - II. A non-linear matter power spectrum interpolator developed using artificial neural networks
• PkANN - I. Non-linear matter power spectrum interpolation through artificial neural networks
• Cosmological parameter estimation via iterative emulation of likelihoods
• Kernel-Based Emulator for the 3D Matter Power Spectrum from CLASS
• Euclid-era cosmology for everyone: Neural net assisted MCMC sampling for the joint 3x2 likelihood
• Combination of cluster number counts and two-point correlations: Validation on Mock Dark Energy Survey
• Neural Network Acceleration of Large-scale Structure Theory Calculations

Cited by in corpus (10)

• Cosmological Constraints from Galaxy Clusters and Groups in the eROSITA Final Equatorial Depth Survey
• CONNECT: A neural network based framework for emulating cosmological observables and cosmological parameter inference
• Capse.jl: efficient and auto-differentiable CMB power spectra emulation
• Fast and robust Bayesian Inference using Gaussian Processes with GPry
• Fast and effortless computation of profile likelihoods using CONNECT
• CombineHarvesterFlow: Joint Probe Analysis Made Easy with Normalizing Flows
• Faster Bayesian inference with neural network bundles and new results for $f(R)$ models
• Informed total-error-minimizing priors: Interpretable cosmological parameter constraints despite complex nuisance effects
• Environmental sustainability in basic research: a perspective from HECAP+
• Variational autoencoder for generating realistic $N$-body simulations for dark matter halos