• DOI:10.3847/1538-3881/abf42e
• Corpus ID: 231879609

Real-time Likelihood-free Inference of Roman Binary Microlensing Events with Amortized Neural Posterior Estimation

@article{Zhang2021RealtimeLI,
  title={Real-time Likelihood-free Inference of Roman Binary Microlensing Events with Amortized Neural Posterior Estimation},
  author={Keming 可名 Zhang 张 and Joshua S. Bloom and B. Scott Gaudi and François Lanusse and Casey Y. Lam and Jessica R. Lu},
  journal={The Astronomical Journal},
  year={2021},
  volume={161}
}

• Keming 可名 Zhang 张, J. Bloom, +3 authors Jessica R. Lu
• Published 11 February 2021
• Computer Science
• The Astronomical Journal

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: the 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 approach named amortized neural posterior estimation, where a neural density estimator (NDE) learns a surrogate posterior as an observation-parameterized 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.