BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Simulating and unfolding LHC events with generative networks - Anj
 a Butter\, University of Heidelberg
DTSTART:20210216T160000Z
DTEND:20210216T170000Z
UID:TALK156067@talks.cam.ac.uk
CONTACT:Heribertus Bayu Hartanto
DESCRIPTION:Over the next years\, measurements at the LHC and the HL-LHC w
 ill provide us with a wealth of data. The best hope of answering fundament
 al questions like the nature of dark matter\, is to adopt big data techniq
 ues in analyses and simulations to extract all relevant information. At th
 e analysis level\, machine learning methods have already shown impressive 
 performance boosts in many areas like top tagging\, jet calibration or par
 ticle identification. On the theory side\, LHC physics crucially relies on
  our ability to simulate events efficiently from first principles. In the 
 coming LHC runs\, these simulations will face unprecedented precision requ
 irements to match the experimental accuracy. Innovative ML techniques like
  generative models can help us overcome limitations from the high dimensio
 nality of the parameter space. Such networks can be employed within establ
 ished simulation tools or as part of a new framework. Since neural network
 s can be inverted\, they also open new avenues in LHC analyses.
LOCATION:https://cern.zoom.us/j/61144924828?pwd=WDB6QmFCMEZiSEN5Q0k2aklWSj
 k5Zz09
END:VEVENT
END:VCALENDAR