BEGIN:VCALENDAR VERSION:2.0 PRODID:-//linuxsoftware.nz//NONSGML Joyous v1.4//EN BEGIN:VEVENT SUMMARY:Neural posterior estimation for gravitational-wave inference DTSTART:20250710T143000Z DTEND:20250710T160000Z DTSTAMP:20260724T080637Z UID:e6abeea7-a905-4977-8194-5600a465ce38 SEQUENCE:1 CREATED:20250708T131233Z DESCRIPTION: I will describe how deep learning and simulation-based infere nce address gravitational-wave data analysis challenges\, including high e vent rates and rapid electromagnetic follow-up. The approach uses simulate d data to train neural networks\, such as normalizing flows\, to accuratel y represent posterior distributions. Once trained\, these models enable ex tremely rapid inference—reducing analyses to seconds. I will highlight r ecent advances in population inference and binary neutron star parameter e stimation\, demonstrating the promise of these techniques for next-generat ion detectors. LAST-MODIFIED:20250708T131233Z LOCATION:DF Seminar Room (2-8.3)\, 2nd floor of Physics Building URL:http://df.vps.tecnico.ulisboa.pt/en/events/neural-posterior-estimation -for-gravitational-wave-inference/ X-ALT-DESC;FMTTYPE=text/html:

I will describe ho w deep learning and simulation-based inference address gravitational-wave data analysis challenges\, including high event rates and rapid electromag netic follow-up.

The approach uses simulated data to train neura l networks\, such as normalizing flows\, to accurately represent posterior distributions. Once trained\, these models enable extremely rapid inferen ce—reducing analyses to seconds. I will highlight recent advances in pop ulation inference and binary neutron star parameter estimation\, demonstra ting the promise of these techniques for next-generation detectors.

END:VEVENT END:VCALENDAR