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:20260630T102704Z UID:e6abeea7-a905-4977-8194-5600a465ce38 SEQUENCE:2 CREATED:20250708T131246Z DESCRIPTION:I will describe how deep learning and simulation-based inferen ce address gravitational-wave data analysis challenges\, including high ev ent rates and rapid electromagnetic follow-up. The approach uses simulated data to train neural networks\, such as normalizing flows\, to accurately represent posterior distributions. Once trained\, these models enable ext remely rapid inference—reducing analyses to seconds. I will highlight re cent advances in population inference and binary neutron star parameter es timation\, demonstrating the promise of these techniques for next-generati on detectors. LAST-MODIFIED:20250708T131259Z LOCATION:DF Seminar Room (2-8.3)\, 2nd floor of Physics Building URL:http://df.vps.tecnico.ulisboa.pt/pt/eventos/neural-posterior-estimatio n-for-gravitational-wave-inference/ X-ALT-DESC;FMTTYPE=text/html:

I will describe how deep learning and simulation-based inference address gravitational-wave d ata analysis challenges\, including high event rates and rapid electromagn etic follow-up.

The approach uses simulated data to train neural networks\, such as normalizing flows\, to accurately represent posterior distributions. Once trained\, these models enable extremely rapid inferenc e—reducing analyses to seconds. I will highlight recent advances in popu lation inference and binary neutron star parameter estimation\, demonstrat ing the promise of these techniques for next-generation detectors.

END:VEVENT END:VCALENDAR