Solving high-dimensional parameter inference: marginal posterior densities & Moment Networks

Abstract

High-dimensional probability density estimation for inference suffers from the "curse of dimensionality". For many physical inference problems, the full posterior distribution is unwieldy and seldom used in practice. Instead, we propose direct estimation of lower-dimensional marginal distributions, bypassing high-dimensional density estimation or high-dimensional Markov chain Monte Carlo (MCMC) sampling. By evaluating the two-dimensional marginal posteriors we can unveil the full-dimensional parameter covariance structure. We additionally propose constructing a simple hierarchy of fast neural regression models, called Moment Networks, that compute increasing moments of any desired lower-dimensional marginal posterior density; these reproduce exact results from analytic posteriors and those obtained from Masked Autoregressive Flows. We demonstrate marginal posterior density estimation using high-dimensional LIGO-like gravitational wave time series and describe applications for problems of fundamental cosmology.

Accepted in the Third Workshop on Machine Learning and the Physical Sciences, NeurIPS 2020, Vancouver, Canada

Cited by in corpus (11)

• The GIGANTES dataset: precision cosmology from voids in the machine learning era
• Fast and Credible Likelihood-Free Cosmology with Truncated Marginal Neural Ratio Estimation
• Cosmology with one galaxy?
• LtU-ILI: An All-in-One Framework for Implicit Inference in Astrophysics and Cosmology
• Forward modeling of galaxy populations for cosmological redshift distribution inference
• GLASS: Generator for Large Scale Structure
• Scalable inference with Autoregressive Neural Ratio Estimation
• An Observationally Driven Multifield Approach for Probing the Circum-Galactic Medium with Convolutional Neural Networks
• Inferring halo masses with Graph Neural Networks
• Weighing the Milky Way and Andromeda with Artificial Intelligence
• APES: Approximate Posterior Ensemble Sampler