Real-Time Gravitational Wave Science with Neural Posterior Estimation

Dax, Maximilian; Green, Stephen; Gair, J. R.; Macke, Jakob H.; Buonanno, A.; Schoelkopf, Bernhard

doi:10.1103/physrevlett.127.241103

Cited by 131 publications

(104 citation statements)

References 44 publications

Supporting

Mentioning

100

Contrasting

Unclassified

Order By: Relevance

“…If the mappings involved (e.g., from parameter settings to target quantities) can be fitted from data, we can employ machine learning, which will often speed them up by orders of magnitude. Such a speed-up can qualitatively change the usability of a model: for instance, we have recently built a system to map gravitational wave measurements to a probability distribution of physical parameters of a black hole merger event, including sky position [27]. The fact that this model only requires seconds to evaluate makes it possible to immediately start electromagnetic follow-up observations using telescopes as soon as a gravitational wave event has been detected, enabling analysis of transient events.…”

Section: Causal Representationmentioning

confidence: 99%

From Statistical to Causal Learning

Schölkopf¹,

Kügelgen²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

We describe basic ideas underlying research to build and understand artificially intelligent systems: from symbolic approaches via statistical learning to interventional models relying on concepts of causality. Some of the hard open problems of machine learning and AI are intrinsically related to causality, and progress may require advances in our understanding of how to model and infer causality from data. *

show abstract

Section: Causal Representationmentioning

confidence: 99%

From Statistical to Causal Learning

Schölkopf¹,

Kügelgen²

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Detecting and characterizing MMA events therefore requires discovery of very rare events with very sparse and heterogeneous data from multiple facilities all in real-time. ML methods, including unsupervised anomaly detection techniques [70], and hybrid architectures such as convolutional recurrent neural networks (CRNNs) [71,72], and simulationbased inference techniques [73] will be necessary to process the smorgasbord of observations from different facilities, flag these events within hours, and automatically trigger follow-up studies. Beyond the ML techniques highlighted in this white paper, MMA will require significant investment in cross-survey cyberinfrastructure to help the community store, process and share a mix of public and private data in order to understand these enigmatic events.…”

Section: Time Domain and Multi-messenger Astrophysicsmentioning

confidence: 99%

Machine Learning and Cosmology

Dvorkin,

Mishra-Sharma,

Nord

et al. 2022

Preprint

View full text Add to dashboard Cite

Methods based on machine learning have recently made substantial inroads in many corners of cosmology. Through this process, new computational tools, new perspectives on data collection, model development, analysis, and discovery, as well as new communities and educational pathways have emerged. Despite rapid progress, substantial potential at the intersection of cosmology and machine learning remains untapped. In this white paper, we summarize current and ongoing developments relating to the application of machine learning within cosmology and provide a set of recommendations aimed at maximizing the scientific impact of these burgeoning tools over the coming decade through both technical development as well as the fostering of emerging communities.

show abstract

“…Simulation-based inference techniques have been used to link models to data in a wide range of problems, reflecting the ubiquity of simulators across the sciences. In physics, SBI is useful from the smallest scales in particle colliders [165,166,167], where it allows us to measure the properties of the Higgs boson with a higher precision and less data, to the largest scales in the modeling of gravitational waves [168,169], stellar streams [170], gravitational lensing [171], and the evolution of the universe [172]. These methods have also been applied to study the evolutionary dynamics of protein networks [173] and in yeast strains [174].…”

Section: Examplesmentioning

confidence: 99%

Simulation Intelligence: Towards a New Generation of Scientific Methods

Lavin¹,

Zenil²,

Krakauer³

et al. 2021

Preprint

View full text Add to dashboard Cite

The original "Seven Motifs" set forth a roadmap of essential methods for the field of scientific computing, where a motif is an algorithmic method that captures a pattern of computation and data movement. 1 We present the Nine Motifs of Simulation Intelligence, a roadmap for the development and integration of the essential algorithms necessary for a merger of scientific computing, scientific simulation, and artificial intelligence. We call this merger simulation intelligence (SI), for short. We argue the motifs of simulation intelligence are interconnected and interdependent, much like the components within the layers of an operating system. Using this metaphor, we explore the nature of each layer of the simulation intelligence "operating system" stack (SI-stack) and the motifs therein:1. Multi-physics and multi-scale modeling 2. Surrogate modeling and emulation 3. Simulation-based inference 4. Causal modeling and inference 5. Agent-based modeling 6. Probabilistic programming 7. Differentiable programming 8. Open-ended optimization Machine programmingWe believe coordinated efforts between motifs offers immense opportunity to accelerate scientific discovery, from solving inverse problems in synthetic biology and climate science, to directing nuclear energy experiments and predicting emergent behavior in socioeconomic settings. We elaborate on each layer of the SI-stack, detailing the state-of-art methods, presenting examples to highlight challenges and opportunities, and advocating for specific ways to advance the motifs and the synergies from their combinations. Advancing and integrating these technologies can enable a robust and efficient hypothesis-simulation-analysis type of scientific method, which we introduce with several use-cases for human-machine teaming and automated science.

show abstract

Real-Time Gravitational Wave Science with Neural Posterior Estimation

Cited by 131 publications

References 44 publications

From Statistical to Causal Learning

From Statistical to Causal Learning

Machine Learning and Cosmology

Simulation Intelligence: Towards a New Generation of Scientific Methods

Contact Info

Product

Resources

About