[Seminar] Real-Time GW Inference with Probabilistic Machine Learning—Maximilian Dax (Dec 11, 2025)

This seminar is part of the 2025–2026 Seminar Series of the Simons Collaboration on Black Holes and Strong Gravity. Title: Real-Time Gravitational-Wave Inference with Probabilistic Machine Learning Speaker: Maximilian Dax Affiliation: ELLIS Institute Tübingen / Max Planck Institute for Intelligent Systems Date: December 11, 2025 In this seminar, Maximilian Dax discusses the computational challenges of large-scale and real-time gravitational-wave data analysis and presents DINGO, a machine learning approach designed to enable fast and accurate gravitational-wave inference. DINGO uses generative neural networks to directly estimate probability distributions over gravitational-wave source parameters. The seminar introduces the core ideas behind DINGO and highlights several machine learning techniques developed to adapt modern simulation-based inference methods to the particular challenges of gravitational-wave data analysis. [About the Speaker] Maximilian Dax is a Principal Investigator at the ELLIS Institute Tübingen and the Max Planck Institute for Intelligent Systems, where he leads the research group for Science and Probabilistic Intelligence. His research focuses on probabilistic machine learning and its applications in science. Before joining ELLIS, he completed his PhD at the Max Planck Institute for Intelligent Systems and the University of Tübingen, and spent time at ETH Zurich and Google Research. [Simons Collaboration on Black Holes and Strong Gravity] The Collaboration brings together researchers in gravitational theory, mathematical relativity, numerical computation, gravitational-wave astrophysics, data analysis, and related fields to advance our understanding of black holes and the strong-gravity regime. More information: https://simonscbhsg.com/