Accelerating astronomical and cosmological inference with Preconditioned Monte Carlo

Abstract

We introduce Preconditioned Monte Carlo (PMC), a novel Monte Carlo method for Bayesian inference that facilitates efficient sampling of probability distributions with non-trivial geometry. PMC utilises a Normalising Flow (NF) in order to decorrelate the parameters of the distribution and then proceeds by sampling from the preconditioned target distribution using an adaptive Sequential Monte Carlo (SMC) scheme. The results produced by PMC include samples from the posterior distribution and an estimate of the model evidence that can be used for parameter inference and model comparison respectively. The aforementioned framework has been thoroughly tested in a variety of challenging target distributions achieving state-of-the-art sampling performance. In the cases of primordial feature analysis and gravitational wave inference, PMC is approximately 50 and 25 times faster respectively than Nested Sampling (NS). We found that in higher dimensional applications the acceleration is even greater. Finally, PMC is directly parallelisable, manifesting linear scaling up to thousands of CPUs.

arXiv comment10 pages, 9 figures. Submitted to MNRAS. Code available at https://github.com/minaskar/pocomc

References in corpus (15)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• 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
• dynesty: A Dynamic Nested Sampling Package for Estimating Bayesian Posteriors and Evidences
• SDSS-III: Massive Spectroscopic Surveys of the Distant Universe, the Milky Way Galaxy, and Extra-Solar Planetary Systems
• The Baryon Oscillation Spectroscopic Survey of SDSS-III
• Bilby: A user-friendly Bayesian inference library for gravitational-wave astronomy
• PolyChord: next-generation nested sampling
• Markov Chain Monte Carlo Methods for Bayesian Data Analysis in Astronomy
• Flow-based generative models for Markov chain Monte Carlo in lattice field theory
• Nested Sampling with Normalising Flows for Gravitational-Wave Inference
• zeus: A Python implementation of Ensemble Slice Sampling for efficient Bayesian parameter inference
• Primordial Features from Linear to Nonlinear Scales
• Accelerated Bayesian inference using deep learning

Cited by in corpus (27)

• The CosmoVerse White Paper: Addressing observational tensions in cosmology with systematics and fundamental physics
• Importance nested sampling with normalising flows
• Modified gravity and massive neutrinos: constraints from the full shape analysis of BOSS galaxies and forecasts for Stage IV surveys
• CosmoPower-JAX: high-dimensional Bayesian inference with differentiable cosmological emulators
• Gravitational imaging through a triple source plane lens: revisiting the $\Lambda$CDM-defying dark subhalo in SDSSJ0946+1006
• SBI++: Flexible, Ultra-fast Likelihood-free Inference Customized for Astronomical Applications
• Interacting dark energy from the joint analysis of the power spectrum and bispectrum multipoles with the EFTofLSS
• Analysis of Unified Galaxy Power Spectrum Multipole Measurements
• Bayesian analysis of (3+1)D relativistic nuclear dynamics with the RHIC beam energy scan data
• Simulating the Detection of the Global 21 cm Signal with MIST for Different Models of the Soil and Beam Directivity
• Primordial feature constraints from BOSS+eBOSS
• Global Bayesian Analysis of $\mathrm{J}/\psi$ Photoproduction on Proton and Lead Targets
• Selecting samples of galaxies with fewer Fingers-of-God
• The Radius of PSR J0437-4715 from NICER Data
• Reducing nuisance prior sensitivity via non-linear reparameterization, with application to EFT analyses of large-scale structure
• Inferring Binary Properties from Gravitational Wave Signals
• Validating Sequential Monte Carlo for Gravitational-Wave Inference
• Bayesian Model Selection and Uncertainty Propagation for Beam Energy Scan Heavy-Ion Collisions
• Robust and fast parameter estimation for gravitational waves from binary neutron star merger remnants
• A comparison of shrinkage estimators of the cosmological precision matrix
• Learning Informed Prior Distributions with Normalizing Flows for Bayesian Analysis
• Chemodynamics of BoötesI with $S^5$: Revised Velocity Gradient, Dark Matter Density, and Galactic Chemical Evolution Constraints
• Pushing spectral siren cosmology into the third-generation era: a blinded mock data challenge
• The SRG/eROSITA All-Sky Survey. Detection of shock-heated gas beyond the halo boundary into the accretion region
• Sequential Kalman Tuning of the $t$-preconditioned Crank-Nicolson algorithm: efficient, adaptive and gradient-free inference for Bayesian inverse problems
• The Sequential Monte Carlo goes NUTS: Boosting Gravitational-Wave Inference
• What We Have Learned from NICER About Neutron Star Radii