Scalable inference with Autoregressive Neural Ratio Estimation

Abstract

In recent years, there has been a remarkable development of simulation-based inference (SBI) algorithms, and they have now been applied across a wide range of astrophysical and cosmological analyses. There are a number of key advantages to these methods, centred around the ability to perform scalable statistical inference without an explicit likelihood. In this work, we propose two technical building blocks to a specific sequential SBI algorithm, truncated marginal neural ratio estimation (TMNRE). In particular, first we develop autoregressive ratio estimation with the aim to robustly estimate correlated high-dimensional posteriors. Secondly, we propose a slice-based nested sampling algorithm to efficiently draw both posterior samples and constrained prior samples from ratio estimators, the latter being instrumental for sequential inference. To validate our implementation, we carry out inference tasks on three concrete examples: a toy model of a multi-dimensional Gaussian, the analysis of a stellar stream mock observation, and finally, a proof-of-concept application to substructure searches in strong gravitational lensing. In addition, we publicly release the code for both the autoregressive ratio estimator and the slice sampler.

arXiv comment12 pages. 6 figures. Codes: swyft is available at https://github.com/undark-lab/swyft , torchns is available at https://github.com/undark-lab/torchns - v2: version accepted by MNRAS

References in corpus (52)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Array Programming with NumPy
• Gaia Data Release 2. Summary of the contents and survey properties
• The Astropy Project: Building an inclusive, open-science project and status of the v2.0 core package
• Deep Residual Learning for Image Recognition
• MultiNest: an efficient and robust Bayesian inference tool for cosmology and particle physics
• The James Webb Space Telescope
• Multimodal nested sampling: an efficient and robust alternative to MCMC methods for astronomical data analysis
• Evidence for substructure in lens galaxies?
• PolyChord: nested sampling for cosmology
• PolyChord: next-generation nested sampling
• Constraining the Milky Way potential with a 6-D phase-space map of the GD-1 stellar stream
• Gravitational detection of a low-mass dark satellite at cosmological distance
• MADE: Masked Autoencoder for Distribution Estimation
• The accretion history of dark matter halos III: A physical model for the concentration-mass relation
• Real-time gravitational-wave science with neural posterior estimation
• The shape of the inner Milky Way halo from observations of the Pal 5 and GD-1 stellar streams
• Analytic models of plausible gravitational lens potentials
• Massive optimal data compression and density estimation for scalable, likelihood-free inference in cosmology
• Nested sampling for physical scientists
• Nuisance hardened data compression for fast likelihood-free inference
• Dissecting the Gravitational Lens B1608+656. I. Lens Potential Reconstruction
• Nested Sampling Methods
• Properties of Dark Subhaloes from Gaps in Tidal Streams
• Gaps in globular cluster streams: giant molecular clouds can cause them too
• Milky Way Mass and Potential Recovery Using Tidal Streams in a Realistic Halo
• Cosmology Intertwined I: Perspectives for the Next Decade
• Effects of baryonic and dark matter substructure on the Pal 5 stream
• Probing the nature of dark matter particles with stellar streams
• Fast and Credible Likelihood-Free Cosmology with Truncated Marginal Neural Ratio Estimation
• Deep Generative Models for Galaxy Image Simulations
• Hierarchical Inference With Bayesian Neural Networks: An Application to Strong Gravitational Lensing
• Large Synoptic Survey Telescope: Dark Energy Science Collaboration
• Implicit Likelihood Inference of Reionization Parameters from the 21 cm Power Spectrum
• A Trust Crisis In Simulation-Based Inference? Your Posterior Approximations Can Be Unfaithful
• SICRET: Supernova Ia Cosmology with truncated marginal neural Ratio EsTimation
• Overview of Approximate Bayesian Computation
• Estimating the warm dark matter mass from strong lensing images with truncated marginal neural ratio estimation
• Robust Simulation-Based Inference in Cosmology with Bayesian Neural Networks
• Towards constraining warm dark matter with stellar streams through neural simulation-based inference
• Truncated proposals for scalable and hassle-free simulation-based inference
• One never walks alone: the effect of the perturber population on subhalo measurements in strong gravitational lenses
• New constraints on the dark matter density profiles of dwarf galaxies from proper motions of globular cluster streams
• Debiasing Standard Siren Inference of the Hubble Constant with Marginal Neural Ratio Estimation
• A Framework for Obtaining Accurate Posteriors of Strong Gravitational Lensing Parameters with Flexible Priors and Implicit Likelihoods using Density Estimation
• Solving high-dimensional parameter inference: marginal posterior densities & Moment Networks
• Targeted Likelihood-Free Inference of Dark Matter Substructure in Strongly-Lensed Galaxies
• Overview of the European Extremely Large Telescope and its instrument suite
• What to do when things get crowded? Scalable joint analysis of overlapping gravitational wave signals
• Detection is truncation: studying source populations with truncated marginal neural ratio estimation
• Slice Sampling
• The Cherenkov Telescope Array

Cited by in corpus (7)

• The Science of the Einstein Telescope
• Cosmology with Persistent Homology: a Fisher Forecast
• Mapping reionization bubbles in the JWST era II: inferring the position and characteristic size of individual bubbles
• Near-instantaneous Atmospheric Retrievals and Model Comparison with FASTER
• STAR NRE: Solving supernova selection effects with set-based truncated auto-regressive neural ratio estimation
• Observable Optimization for Precision Theory: Machine Learning Energy Correlators
• On the Energy Distribution of the Galactic Center Excess' Sources