Timezone: »
Gravitational waves (GWs) detected by the LIGO and Virgo observatories encode descriptions of their astrophysical progenitors. To characterize these systems, physical GW signal models are inverted using Bayesian inference coupled with stochastic samplers---a task that can take O(day) for a typical binary black hole. Several recent efforts have attempted to speed this up by using normalizing flows to estimate the posterior distribution conditioned on the observed data. In this study, we further develop these techniques to achieve results nearly indistinguishable from standard samplers when evaluated on real GW data, with inference times of one minute per event. This is enabled by (i) incorporating detector nonstationarity from event to event by conditioning on a summary of the noise characteristics, (ii) using an embedding network adapted to GW signals to compress data, and (iii) adopting a new inference algorithm that makes use of underlying physical equivariances.
Author Information
Maximilian Dax (MPI for Intelligent Systems, Tübingen)
Atilim Gunes Baydin (University of Oxford)
More from the Same Authors
-
2021 : Amortized Bayesian inference of gravitational waves with normalizing flows »
Maximilian Dax · Stephen Green · Jakob Macke · Bernhard Schölkopf -
2021 : Learning the solar latent space: sigma-variational autoencoders for multiple channel solar imaging »
Edward Brown · Christopher Bridges · Bernard Benson · Atilim Gunes Baydin -
2021 : Simultaneous Multivariate Forecast of Space Weather Indices using Deep Neural Network Ensembles »
Bernard Benson · Christopher Bridges · Atilim Gunes Baydin -
2021 : Dropout and Ensemble Networks for Thermospheric Density Uncertainty Estimation »
Stefano Bonasera · Giacomo Acciarini · Jorge Pérez-Hernández · Bernard Benson · Edward Brown · Eric Sutton · Moriba Jah · Christopher Bridges · Atilim Gunes Baydin -
2022 : Inferring molecular complexity from mass spectrometry data using machine learning »
Timothy Gebhard · Aaron C. Bell · Jian Gong · Jaden J. A. Hastings · George Fricke · Nathalie Cabrol · Scott Sandford · Michael Phillips · Kimberley Warren-Rhodes · Atilim Gunes Baydin -
2022 : Addressing out-of-distribution data for flow-based gravitational wave inference »
Maximilian Dax · Stephen Green · Jonas Wildberger · Jonathan Gair · Michael Puerrer · Jakob Macke · Alessandra Buonanno · Bernhard Schölkopf -
2023 Poster: Flow Matching for Scalable Simulation-Based Inference »
Jonas Wildberger · Maximilian Dax · Simon Buchholz · Stephen Green · Jakob H Macke · Bernhard Schölkopf -
2023 Workshop: NeurIPS 2023 Workshop: Machine Learning and the Physical Sciences »
Brian Nord · Atilim Gunes Baydin · Adji Bousso Dieng · Emine Kucukbenli · Siddharth Mishra-Sharma · Benjamin Nachman · Kyle Cranmer · Gilles Louppe · Savannah Thais -
2022 Workshop: Machine Learning and the Physical Sciences »
Atilim Gunes Baydin · Adji Bousso Dieng · Emine Kucukbenli · Gilles Louppe · Siddharth Mishra-Sharma · Benjamin Nachman · Brian Nord · Savannah Thais · Anima Anandkumar · Kyle Cranmer · Lenka Zdeborová · Rianne van den Berg -
2021 : Session 3 | Invited talk: Laure Zanna, "The future of climate modeling in the age of machine learning" »
Laure Zanna · Atilim Gunes Baydin -
2021 : Session 3 | Invited talk: Surya Ganguli, "From the geometry of high dimensional energy landscapes to optimal annealing in a dissipative many body quantum optimizer" »
Surya Ganguli · Atilim Gunes Baydin -
2021 : Session 2 | Contributed talk: George Stein, "Self-supervised similarity search for large scientific datasets" »
George Stein · Atilim Gunes Baydin -
2021 : Session 2 | Invited talk: Megan Ansdell, "NASA's efforts & opportunities to support ML in the Physical Sciences" »
Megan Ansdell · Atilim Gunes Baydin -
2021 : Session 1 | Contributed talk: Tian Xie, "Crystal Diffusion Variational Autoencoder for Periodic Material Generation" »
Tian Xie · Atilim Gunes Baydin -
2021 : Session 1 | Invited talk: Bingqing Cheng, "Predicting material properties with the help of machine learning" »
Bingqing Cheng · Atilim Gunes Baydin -
2021 : Session 1 | Invited talk: Max Welling, "Accelerating simulations of nature, both classical and quantum, with equivariant deep learning" »
Max Welling · Atilim Gunes Baydin -
2021 Workshop: Machine Learning and the Physical Sciences »
Anima Anandkumar · Kyle Cranmer · Mr. Prabhat · Lenka Zdeborová · Atilim Gunes Baydin · Juan Carrasquilla · Emine Kucukbenli · Gilles Louppe · Benjamin Nachman · Brian Nord · Savannah Thais -
2021 Poster: Domain Invariant Representation Learning with Domain Density Transformations »
A. Tuan Nguyen · Toan Tran · Yarin Gal · Atilim Gunes Baydin -
2020 : Session 3 | Invited talk: Laura Waller, "Physics-based Learning for Computational Microscopy" »
Laura Waller · Atilim Gunes Baydin -
2020 : Session 2 | Invited talk: Phiala Shanahan, "Generative Flow Models for Gauge Field Theory" »
Phiala Shanahan · Atilim Gunes Baydin -
2020 : Session 2 | Invited talk: Estelle Inack, "Variational Neural Annealing" »
Estelle Inack · Atilim Gunes Baydin -
2020 : Session 1 | Invited talk: Michael Bronstein, "Geometric Deep Learning for Functional Protein Design" »
Michael Bronstein · Atilim Gunes Baydin -
2020 : Session 1 | Invited talk: Lauren Anderson, "3D Milky Way Dust Map using a Scalable Gaussian Process" »
Lauren Anderson · Atilim Gunes Baydin -
2020 Workshop: Machine Learning and the Physical Sciences »
Anima Anandkumar · Kyle Cranmer · Shirley Ho · Mr. Prabhat · Lenka Zdeborová · Atilim Gunes Baydin · Juan Carrasquilla · Adji Bousso Dieng · Karthik Kashinath · Gilles Louppe · Brian Nord · Michela Paganini · Savannah Thais -
2020 Poster: Black-Box Optimization with Local Generative Surrogates »
Sergey Shirobokov · Vladislav Belavin · Michael Kagan · Andrei Ustyuzhanin · Atilim Gunes Baydin -
2019 : Opening Remarks »
Atilim Gunes Baydin · Juan Carrasquilla · Shirley Ho · Karthik Kashinath · Michela Paganini · Savannah Thais · Anima Anandkumar · Kyle Cranmer · Roger Melko · Mr. Prabhat · Frank Wood -
2019 Workshop: Machine Learning and the Physical Sciences »
Atilim Gunes Baydin · Juan Carrasquilla · Shirley Ho · Karthik Kashinath · Michela Paganini · Savannah Thais · Anima Anandkumar · Kyle Cranmer · Roger Melko · Mr. Prabhat · Frank Wood -
2019 Workshop: Program Transformations for ML »
Pascal Lamblin · Atilim Gunes Baydin · Alexander Wiltschko · Bart van Merriënboer · Emily Fertig · Barak Pearlmutter · David Duvenaud · Laurent Hascoet -
2019 Poster: Efficient Probabilistic Inference in the Quest for Physics Beyond the Standard Model »
Atilim Gunes Baydin · Lei Shao · Wahid Bhimji · Lukas Heinrich · Saeid Naderiparizi · Andreas Munk · Jialin Liu · Bradley Gram-Hansen · Gilles Louppe · Lawrence Meadows · Philip Torr · Victor Lee · Kyle Cranmer · Mr. Prabhat · Frank Wood -
2017 : Panel discussion »
Atilim Gunes Baydin · Adam Paszke · Jonathan Hüser · Jean Utke · Laurent Hascoet · Jeffrey Siskind · Jan Hueckelheim · Andreas Griewank -
2017 : Beyond backprop: automatic differentiation in machine learning »
Atilim Gunes Baydin -
2017 Workshop: Deep Learning for Physical Sciences »
Atilim Gunes Baydin · Mr. Prabhat · Kyle Cranmer · Frank Wood