Hyperparameter Optimization of an hp-Greedy Reduced Basis for Gravitational Wave Surrogates
In a previous work, we introduced, in the context of gravitational wave science, an initial study on an automated domain-decomposition approach for a reduced basis through hp-greedy refinement. The approach constructs local reduced bases of lower dimensionality than global ones, with the same or hig...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-12-01
|
Series: | Universe |
Subjects: | |
Online Access: | https://www.mdpi.com/2218-1997/10/1/6 |
_version_ | 1797342440614526976 |
---|---|
author | Franco Cerino J. Andrés Diaz-Pace Emmanuel A. Tassone Manuel Tiglio Atuel Villegas |
author_facet | Franco Cerino J. Andrés Diaz-Pace Emmanuel A. Tassone Manuel Tiglio Atuel Villegas |
author_sort | Franco Cerino |
collection | DOAJ |
description | In a previous work, we introduced, in the context of gravitational wave science, an initial study on an automated domain-decomposition approach for a reduced basis through hp-greedy refinement. The approach constructs local reduced bases of lower dimensionality than global ones, with the same or higher accuracy. These “light” local bases should imply both faster evaluations when predicting new waveforms and faster data analysis, particularly faster statistical inference (the forward and inverse problems, respectively). In this approach, however, we have previously found important dependence on several hyperparameters, which do not appear in a global reduced basis. This naturally leads to the problem of hyperparameter optimization (HPO), which is the subject of this paper. Here, we compare the efficiency of the Bayesian approach against grid and random searches, which are two order of magnitude slower. Then, we tackle the problem of HPO through Bayesian optimization.We find that, for the cases studied here of gravitational waves from the collision of two spinning but non-precessing black holes, for the same accuracy, local hp-greedy reduced bases with HPO have a lower dimensionality of up to 4×, depending on the desired accuracy. This factor should directly translate into a parameter estimation speedup in the context of reduced order quadratures, for instance. Such acceleration might help in the near real-time requirements for electromagnetic counterparts of gravitational waves from compact binary coalescences. The code developed for this project is available open source from public repositories. This paper is an invited contribution to the Special Issue “Recent Advances in Gravity: A Themed Issue in Honor of Prof. Jorge Pullin on his 60th Anniversary”. |
first_indexed | 2024-03-08T10:33:20Z |
format | Article |
id | doaj.art-5039b83298724e898168c8601a9579d3 |
institution | Directory Open Access Journal |
issn | 2218-1997 |
language | English |
last_indexed | 2024-03-08T10:33:20Z |
publishDate | 2023-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Universe |
spelling | doaj.art-5039b83298724e898168c8601a9579d32024-01-26T18:42:55ZengMDPI AGUniverse2218-19972023-12-01101610.3390/universe10010006Hyperparameter Optimization of an hp-Greedy Reduced Basis for Gravitational Wave SurrogatesFranco Cerino0J. Andrés Diaz-Pace1Emmanuel A. Tassone2Manuel Tiglio3Atuel Villegas4CONICET, Córdoba 5000, ArgentinaISISTAN-CONICET Research Institute, UNICEN University, Tandil 7000, ArgentinaCONICET, Córdoba 5000, ArgentinaCONICET, Córdoba 5000, ArgentinaFacultad de Ciencias Exactas y Tecnología, Universidad Nacional de Tucumán, San Miguel de Tucumán 4000, ArgentinaIn a previous work, we introduced, in the context of gravitational wave science, an initial study on an automated domain-decomposition approach for a reduced basis through hp-greedy refinement. The approach constructs local reduced bases of lower dimensionality than global ones, with the same or higher accuracy. These “light” local bases should imply both faster evaluations when predicting new waveforms and faster data analysis, particularly faster statistical inference (the forward and inverse problems, respectively). In this approach, however, we have previously found important dependence on several hyperparameters, which do not appear in a global reduced basis. This naturally leads to the problem of hyperparameter optimization (HPO), which is the subject of this paper. Here, we compare the efficiency of the Bayesian approach against grid and random searches, which are two order of magnitude slower. Then, we tackle the problem of HPO through Bayesian optimization.We find that, for the cases studied here of gravitational waves from the collision of two spinning but non-precessing black holes, for the same accuracy, local hp-greedy reduced bases with HPO have a lower dimensionality of up to 4×, depending on the desired accuracy. This factor should directly translate into a parameter estimation speedup in the context of reduced order quadratures, for instance. Such acceleration might help in the near real-time requirements for electromagnetic counterparts of gravitational waves from compact binary coalescences. The code developed for this project is available open source from public repositories. This paper is an invited contribution to the Special Issue “Recent Advances in Gravity: A Themed Issue in Honor of Prof. Jorge Pullin on his 60th Anniversary”.https://www.mdpi.com/2218-1997/10/1/6gravitational wave surrogatesreduced basismachine learning |
spellingShingle | Franco Cerino J. Andrés Diaz-Pace Emmanuel A. Tassone Manuel Tiglio Atuel Villegas Hyperparameter Optimization of an hp-Greedy Reduced Basis for Gravitational Wave Surrogates Universe gravitational wave surrogates reduced basis machine learning |
title | Hyperparameter Optimization of an hp-Greedy Reduced Basis for Gravitational Wave Surrogates |
title_full | Hyperparameter Optimization of an hp-Greedy Reduced Basis for Gravitational Wave Surrogates |
title_fullStr | Hyperparameter Optimization of an hp-Greedy Reduced Basis for Gravitational Wave Surrogates |
title_full_unstemmed | Hyperparameter Optimization of an hp-Greedy Reduced Basis for Gravitational Wave Surrogates |
title_short | Hyperparameter Optimization of an hp-Greedy Reduced Basis for Gravitational Wave Surrogates |
title_sort | hyperparameter optimization of an hp greedy reduced basis for gravitational wave surrogates |
topic | gravitational wave surrogates reduced basis machine learning |
url | https://www.mdpi.com/2218-1997/10/1/6 |
work_keys_str_mv | AT francocerino hyperparameteroptimizationofanhpgreedyreducedbasisforgravitationalwavesurrogates AT jandresdiazpace hyperparameteroptimizationofanhpgreedyreducedbasisforgravitationalwavesurrogates AT emmanuelatassone hyperparameteroptimizationofanhpgreedyreducedbasisforgravitationalwavesurrogates AT manueltiglio hyperparameteroptimizationofanhpgreedyreducedbasisforgravitationalwavesurrogates AT atuelvillegas hyperparameteroptimizationofanhpgreedyreducedbasisforgravitationalwavesurrogates |