BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:(Machine) learning amplitudes for faster event generation - Fady B
 ishara (Desy)
DTSTART:20200528T150000Z
DTEND:20200528T160000Z
UID:TALK141484@talks.cam.ac.uk
CONTACT:Mathieu Pellen
DESCRIPTION:*The seminar will take place via vidyo "here":https://indico.c
 ern.ch/event/908074/ .\nThe explicit url is: https://indico.cern.ch/event/
 908074/ .*\n\nIn [1912.11055] we proposed to replace the exact squared-amp
 litudes used in monte carlo (MC) event generators with approximate\, albei
 t very precise\, ones in the form of pre-trained machine learning (ML) reg
 ressors. The idea is to speed up the evaluation of the numerically expensi
 ve functions that arise in loop computations. This approach also alleviate
 s the need for quadruple and higher precision arithmetic during event gene
 ration. In this talk I will start by discussing a proof of principle that 
 demonstrates the efficacy of this proposal. In the rest of the talk\, I wi
 ll discuss our progress towards the ultimate goal of approximating buildin
 g blocks of NNLO squared-amplitudes where the gain in evaluation speed can
  be even more dramatic.
LOCATION:Virtual Seminar 
END:VEVENT
END:VCALENDAR