Rapid Likelihood Free Inference of Compact Binary Coalescences using Accelerated Hardware
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910544718462976 |
|---|---|
| author | Chatterjee, Deep Marx, Ethan Benoit, William Kumar, Ravi Desai, Malina Govorkova, Ekaterina Gunny, Alec Moreno, Eric Omer, Rafia Raikman, Ryan Saleem, Muhammed Aggarwal, Shrey Coughlin, Michael W. Harris, Philip Katsavounidis, Erik |
| author_facet | Chatterjee, Deep Marx, Ethan Benoit, William Kumar, Ravi Desai, Malina Govorkova, Ekaterina Gunny, Alec Moreno, Eric Omer, Rafia Raikman, Ryan Saleem, Muhammed Aggarwal, Shrey Coughlin, Michael W. Harris, Philip Katsavounidis, Erik |
| contents | 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 $\sim 6$ million trainable parameters with training times $\lesssim 24$ 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 $\sim 6$s. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_19048 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Rapid Likelihood Free Inference of Compact Binary Coalescences using Accelerated Hardware Chatterjee, Deep Marx, Ethan Benoit, William Kumar, Ravi Desai, Malina Govorkova, Ekaterina Gunny, Alec Moreno, Eric Omer, Rafia Raikman, Ryan Saleem, Muhammed Aggarwal, Shrey Coughlin, Michael W. Harris, Philip Katsavounidis, Erik General Relativity and Quantum Cosmology Instrumentation and Methods for Astrophysics Machine Learning 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 $\sim 6$ million trainable parameters with training times $\lesssim 24$ 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 $\sim 6$s. |
| title | Rapid Likelihood Free Inference of Compact Binary Coalescences using Accelerated Hardware |
| topic | General Relativity and Quantum Cosmology Instrumentation and Methods for Astrophysics Machine Learning |
| url | https://arxiv.org/abs/2407.19048 |