alpha-Deep Probabilistic Inference (alpha-DPI): efficient uncertainty quantification from exoplanet astrometry to black hole feature extraction

TL;DR

This paper introduces alpha-DPI, a deep learning-based method that combines variational inference and importance re-weighting to efficiently and accurately estimate posteriors in complex astronomical inverse problems.

Contribution

The paper presents alpha-DPI, a novel framework that improves posterior estimation speed and accuracy in high-dimensional astronomical inference tasks by integrating alpha-divergence variational inference with importance re-weighting.

Findings

Alpha-DPI achieves faster inference than traditional sampling methods.

It provides more accurate posterior estimates compared to standard variational approaches.

Successfully applied to real astronomical data for exoplanet and black hole analysis.

Abstract

Inference is crucial in modern astronomical research, where hidden astrophysical features and patterns are often estimated from indirect and noisy measurements. Inferring the posterior of hidden features, conditioned on the observed measurements, is essential for understanding the uncertainty of results and downstream scientific interpretations. Traditional approaches for posterior estimation include sampling-based methods and variational inference. However, sampling-based methods are typically slow for high-dimensional inverse problems, while variational inference often lacks estimation accuracy. In this paper, we propose alpha-DPI, a deep learning framework that first learns an approximate posterior using alpha-divergence variational inference paired with a generative neural network, and then produces more accurate posterior samples through importance re-weighting of the network samples. It inherits strengths from both sampling and variational inference methods: it is fast, accurate, and scalable to high-dimensional problems. We apply our approach to two high-impact astronomical inference problems using real data: exoplanet astrometry and black hole feature extraction.