Lightweight posterior construction for gravitational-wave catalogs with the Kolmogorov-Arnold network

Abstract

Neural density estimation has seen widespread applications in the gravitational-wave (GW) data analysis, which enables real-time parameter estimation for compact binary coalescences and enhances rapid inference for subsequent analysis such as population inference. In this work, we explore the application of using the Kolmogorov-Arnold network (KAN) to construct efficient and interpretable neural density estimators for lightweight posterior construction of GW catalogs. By replacing conventional activation functions with learnable splines, KAN achieves superior interpretability, higher accuracy, and greater parameter efficiency on related scientific tasks. Leveraging this feature, we propose a KAN-based neural density estimator, which ingests megabyte-scale GW posterior samples and compresses them into model weights of tens of kilobytes. Subsequently, analytic expressions requiring only several kilobytes can be further distilled from these neural network weights with minimal accuracy trade-off. In practice, GW posterior samples with fidelity can be regenerated rapidly using the model weights or analytic expressions for subsequent analysis. Our lightweight posterior construction strategy is expected to facilitate user-level data storage and transmission, paving a path for efficient analysis of numerous GW events in the next-generation GW detectors.

17 pages, 12 figures; accepted by PRD. Code is publicly available at https://github.com/liu-ws/KMADE

References in corpus (57)

• Observation of Gravitational Waves from a Binary Black Hole Merger
• Advanced Virgo: a 2nd generation interferometric gravitational wave detector
• GWTC-1: A Gravitational-Wave Transient Catalog of Compact Binary Mergers Observed by LIGO and Virgo during the First and Second Observing Runs
• Advanced LIGO
• GW170817: Measurements of Neutron Star Radii and Equation of State
• GWTC-2: Compact Binary Coalescences Observed by LIGO and Virgo During the First Half of the Third Observing Run
• dynesty: A Dynamic Nested Sampling Package for Estimating Bayesian Posteriors and Evidences
• GWTC-3: Compact Binary Coalescences Observed by LIGO and Virgo During the Second Part of the Third Observing Run
• Normalizing Flows: An Introduction and Review of Current Methods
• A gravitational-wave standard siren measurement of the Hubble constant
• Binary Black Hole Population Properties Inferred from the First and Second Observing Runs of Advanced LIGO and Advanced Virgo
• Open data from the first and second observing runs of Advanced LIGO and Advanced Virgo
• KAGRA: 2.5 Generation Interferometric Gravitational Wave Detector
• I-Love-Q Relations in Neutron Stars and their Applications to Astrophysics, Gravitational Waves and Fundamental Physics
• An introduction to Bayesian inference in gravitational-wave astronomy: parameter estimation, model selection, and hierarchical models
• Extracting distribution parameters from multiple uncertain observations with selection biases
• Science with the Einstein Telescope: a comparison of different designs
• Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data
• Open data from the third observing run of LIGO, Virgo, KAGRA and GEO
• First measurement of the Hubble constant from a dark standard siren using the Dark Energy Survey galaxies and the LIGO/Virgo binary-black-hole merger GW170814
• Markov Chain Monte Carlo Methods for Bayesian Data Analysis in Astronomy
• Real-time gravitational-wave science with neural posterior estimation
• Constraints on the cosmic expansion history from GWTC-3
• A gravitational-wave measurement of the Hubble constant following the second observing run of Advanced LIGO and Virgo
• Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomy
• Non-parametric inference of the neutron star equation of state from gravitational wave observations
• Kolmogorov Arnold Informed neural network: A physics-informed deep learning framework for solving forward and inverse problems based on Kolmogorov Arnold Networks
• Gravitational-wave parameter estimation with autoregressive neural network flows
• Eccentric, nonspinning, inspiral, Gaussian-process merger approximant for the detection and characterization of eccentric binary black hole mergers
• Forecasting the detection capabilities of third-generation gravitational-wave detectors using $\text{GWFAST}$
• Tests of General Relativity with GWTC-3
• PESummary: the code agnostic Parameter Estimation Summary page builder
• Inferring the population properties of binary neutron stars with gravitational-wave measurements of spin
• Biases in parameter estimation from overlapping gravitational-wave signals in the third generation detector era
• Listening to the Universe with Next Generation Ground-Based Gravitational-Wave Detectors
• Deep learning and Bayesian inference of gravitational-wave populations: Hierarchical black-hole mergers
• The population properties of spinning black holes using Gravitational-wave Transient Catalog 3
• Real-time gravitational-wave inference for binary neutron stars using machine learning
• Hierarchical Inference of Binary Neutron Star Mass Distribution and Equation of State with Gravitational Waves
• Accumulating errors in tests of general relativity with gravitational waves: overlapping signals and inaccurate waveforms
• Normalizing flows as an avenue to study overlapping gravitational wave signals
• Detectability and parameter estimation of stellar origin black hole binaries with next generation gravitational wave detectors
• Impacts of overlapping gravitational-wave signals on the parameter estimation: Toward the search for cosmological backgrounds
• Improved deep learning techniques in gravitational-wave data analysis
• Gravitational wave populations and cosmology with neural posterior estimation
• Neutron stars as extreme laboratories for gravity tests
• Density estimation with Gaussian processes for gravitational-wave posteriors
• Kolmogorov-Arnold networks in nuclear binding energy prediction
• Extending the Fisher Information Matrix in Gravitational-wave Data Analysis
• Decoding Long-duration Gravitational Waves from Binary Neutron Stars with Machine Learning: Parameter Estimation and Equations of State
• Quick recipes for gravitational-wave selection effects
• Deep learning inference of the neutron star equation of state
• Fast and accurate parameter estimation of high-redshift sources with the Einstein Telescope
• Vetting quark-star models with gravitational waves in the hierarchical Bayesian framework
• Mass function of stellar black holes as revealed by the LIGO-Virgo-KAGRA observations
• Rapid Parameter Estimation for Merging Massive Black Hole Binaries Using Continuous Normalizing Flows
• Inferring the spin distribution of binary black holes using deep learning