Saved in:
Bibliographic Details
Main Authors: Zhu, Xihua, Yang, Yiqian, Zhang, Fan
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.08672
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910750556028928
author Zhu, Xihua
Yang, Yiqian
Zhang, Fan
author_facet Zhu, Xihua
Yang, Yiqian
Zhang, Fan
contents With the rapid development of gravitational wave astronomy, the increasing number of detected events necessitates efficient methods for parameter estimation and model updates. This study presents a novel approach using knowledge distillation techniques to enhance computational efficiency in gravitational wave analysis. We develop a framework combining ResNet1D and Inverse Autoregressive Flow (IAF) architectures, where knowledge from a complex teacher model is transferred to a lighter student model. Our experimental results show that the student model achieves a validation loss of 3.70 with optimal configuration (40,100,0.75), compared to the teacher model's 4.09, while reducing the number of parameters by 43\%. The Jensen-Shannon divergence between teacher and student models remains below 0.0001 across network layers, indicating successful knowledge transfer. By optimizing ResNet layers (7-16) and hidden features (70-120), we achieve a 35\% reduction in inference time while maintaining parameter estimation accuracy. This work demonstrates significant improvements in computational efficiency for gravitational wave data analysis, providing valuable insights for real-time event processing.
format Preprint
id arxiv_https___arxiv_org_abs_2412_08672
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Efficient Gravitational Wave Parameter Estimation via Knowledge Distillation: A ResNet1D-IAF Approach
Zhu, Xihua
Yang, Yiqian
Zhang, Fan
General Relativity and Quantum Cosmology
Instrumentation and Methods for Astrophysics
Machine Learning
Data Analysis, Statistics and Probability
I.2.6
With the rapid development of gravitational wave astronomy, the increasing number of detected events necessitates efficient methods for parameter estimation and model updates. This study presents a novel approach using knowledge distillation techniques to enhance computational efficiency in gravitational wave analysis. We develop a framework combining ResNet1D and Inverse Autoregressive Flow (IAF) architectures, where knowledge from a complex teacher model is transferred to a lighter student model. Our experimental results show that the student model achieves a validation loss of 3.70 with optimal configuration (40,100,0.75), compared to the teacher model's 4.09, while reducing the number of parameters by 43\%. The Jensen-Shannon divergence between teacher and student models remains below 0.0001 across network layers, indicating successful knowledge transfer. By optimizing ResNet layers (7-16) and hidden features (70-120), we achieve a 35\% reduction in inference time while maintaining parameter estimation accuracy. This work demonstrates significant improvements in computational efficiency for gravitational wave data analysis, providing valuable insights for real-time event processing.
title Efficient Gravitational Wave Parameter Estimation via Knowledge Distillation: A ResNet1D-IAF Approach
topic General Relativity and Quantum Cosmology
Instrumentation and Methods for Astrophysics
Machine Learning
Data Analysis, Statistics and Probability
I.2.6
url https://arxiv.org/abs/2412.08672