α-deep Probabilistic Inference ( α-DPI): Efficient Uncertainty Quantification from Exoplanet Astrometry to Black Hole Feature Extraction

He Sun*, Katherine L. Bouman, Paul Tiede, Jason J. Wang, Sarah Blunt, Dimitri Mawet

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

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 (VI). However, sampling-based methods are typically slow for high-dimensional inverse problems, while VI often lacks estimation accuracy. In this paper, we propose α-deep probabilistic inference, a deep learning framework that first learns an approximate posterior using α-divergence VI paired with a generative neural network, and then produces more accurate posterior samples through importance reweighting of the network samples. It inherits strengths from both sampling and VI methods: it is fast, accurate, and more scalable to high-dimensional problems than conventional sampling-based approaches. We apply our approach to two high-impact astronomical inference problems using real data: exoplanet astrometry and black hole feature extraction.

Original languageEnglish (US)
Article number99
JournalAstrophysical Journal
Volume932
Issue number2
DOIs
StatePublished - Jun 1 2022

ASJC Scopus subject areas

  • Astronomy and Astrophysics
  • Space and Planetary Science

Fingerprint

Dive into the research topics of 'α-deep Probabilistic Inference ( α-DPI): Efficient Uncertainty Quantification from Exoplanet Astrometry to Black Hole Feature Extraction'. Together they form a unique fingerprint.

Cite this