English

Rapid Likelihood Free Inference of Compact Binary Coalescences using Accelerated Hardware

General Relativity and Quantum Cosmology 2024-07-30 v1 Instrumentation and Methods for Astrophysics Machine Learning

Abstract

We report a gravitational-wave parameter estimation algorithm, AMPLFI, based on likelihood-free inference using normalizing flows. The focus of AMPLFI is to perform real-time parameter estimation for candidates detected by machine-learning based compact binary coalescence search, Aframe. We present details of our algorithm and optimizations done related to data-loading and pre-processing on accelerated hardware. We train our model using binary black-hole (BBH) simulations on real LIGO-Virgo detector noise. Our model has 6\sim 6 million trainable parameters with training times 24\lesssim 24 hours. Based on online deployment on a mock data stream of LIGO-Virgo data, Aframe + AMPLFI is able to pick up BBH candidates and infer parameters for real-time alerts from data acquisition with a net latency of 6\sim 6s.

Keywords

Cite

@article{arxiv.2407.19048,
  title  = {Rapid Likelihood Free Inference of Compact Binary Coalescences using Accelerated Hardware},
  author = {Deep Chatterjee and Ethan Marx and William Benoit and Ravi Kumar and Malina Desai and Ekaterina Govorkova and Alec Gunny and Eric Moreno and Rafia Omer and Ryan Raikman and Muhammed Saleem and Shrey Aggarwal and Michael W. Coughlin and Philip Harris and Erik Katsavounidis},
  journal= {arXiv preprint arXiv:2407.19048},
  year   = {2024}
}

Comments

Submitted to MLST

R2 v1 2026-06-28T17:55:09.676Z