Automating Inference of Binary Microlensing Events with Neural Density Estimation

Abstract

Automated inference of binary microlensing events with traditional sampling-based algorithms such as MCMC has been hampered by the slowness of the physical forward model and the pathological likelihood surface. Current analysis of such events requires both expert knowledge and large-scale grid searches to locate the approximate solution as a prerequisite to MCMC posterior sampling. As the next generation, space-based microlensing survey with the Roman Space Observatory is expected to yield thousands of binary microlensing events, a new scalable and automated approach is desired. Here, we present an automated inference method based on neural density estimation (NDE). We show that the NDE trained on simulated Roman data not only produces fast, accurate, and precise posteriors but also captures expected posterior degeneracies. A hybrid NDE-MCMC framework can further be applied to produce the exact posterior.

arXiv comment7 pages, 1 figure. This article is superseded by arXiv:2102.05673. Accepted to the ML4PS workshop at NeurIPS 2020

References in corpus (7)

• WaveNet: A Generative Model for Raw Audio
• The frontier of simulation-based inference
• Wide-Field InfrarRed Survey Telescope-Astrophysics Focused Telescope Assets WFIRST-AFTA 2015 Report
• Density estimation using Real NVP
• MADE: Masked Autoencoder for Distribution Estimation
• Predictions of the WFIRST Microlensing Survey I: Bound Planet Detection Rates
• Simulation of a Space-Based Microlensing Survey for Terrestrial Extra-Solar Planets

Cited by in corpus (2)

• Real-Time Likelihood-Free Inference of Roman Binary Microlensing Events with Amortized Neural Posterior Estimation
• A microlensing search of 700 million VVV light curves