# Real-Time Likelihood-Free Inference of Roman Binary Microlensing Events with Amortized Neural Posterior Estimation

arXiv: https://arxiv.org/abs/2102.05673 · HTML: https://mlsanity.com/paper/2102.05673/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 29 references that are in the map.
- First posted on arXiv 10 Feb 2021.

## Builds on (most cited first, 1 of 1)

- [The frontier of simulation-based inference](https://mlsanity.com/paper/1911.01429/) (2019)

## Built on by (most cited first, 8 of 8)

- [Accelerated Bayesian SED Modeling using Amortized Neural Posterior Estimation](https://mlsanity.com/paper/2203.07391/) (2022)
- [Fast and robust Bayesian Inference using Gaussian Processes with GPry](https://mlsanity.com/paper/2211.02045/) (2022)
- [nbi: the Astronomer's Package for Neural Posterior Estimation](https://mlsanity.com/paper/2312.03824/) (2023)
- [A Ubiquitous Unifying Degeneracy in Two-Body Microlensing Systems](https://mlsanity.com/paper/2111.13696/) (2021)
- [MAGIC: Microlensing Analysis Guided by Intelligent Computation](https://mlsanity.com/paper/2206.08199/) (2022)
- [Monte Carlo Techniques for Addressing Large Errors and Missing Data in Simulation-based Inference](https://mlsanity.com/paper/2211.03747/) (2022)
- [Stellar Spectra Fitting with Amortized Neural Posterior Estimation and nbi](https://mlsanity.com/paper/2312.05687/) (2023)
- [Neural Posterior Estimation for Cataloging Astronomical Images from the Legacy Survey of Space and Time](https://mlsanity.com/paper/2510.15315/) (2025)

## Abstract (arXiv)

Fast and automated inference of binary-lens, single-source (2L1S) microlensing events with sampling-based Bayesian algorithms (e.g., Markov Chain Monte Carlo; MCMC) is challenged on two fronts: high computational cost of likelihood evaluations with microlensing simulation codes, and a pathological parameter space where the negative-log-likelihood surface can contain a multitude of local minima that are narrow and deep. Analysis of 2L1S events usually involves grid searches over some parameters to locate approximate solutions as a prerequisite to posterior sampling, an expensive process that often requires human-in-the-loop domain expertise. As the next-generation, space-based microlensing survey with the Roman Space Telescope is expected to yield thousands of binary microlensing events, a new fast and automated method is desirable. Here, we present a likelihood-free inference (LFI) approach named amortized neural posterior estimation, where a neural density estimator (NDE) learns a surrogate posterior hatp(θ|x) as an observation-parametrized conditional probability distribution, from pre-computed simulations over the full prior space. Trained on 291,012 simulated Roman-like 2L1S simulations, the NDE produces accurate and precise posteriors within seconds for any observation within the prior support without requiring a domain expert in the loop, thus allowing for real-time and automated inference. We show that the NDE also captures expected posterior degeneracies. The NDE posterior could then be refined into the exact posterior with a downstream MCMC sampler with minimal burn-in steps.