Choose timezone
Your profile timezone:
EP R&D Software Working Group Meeting
→
Europe/Zurich
32/1-A24 (CERN)
Videoconference
EP R&D Software Working Group Meeting
- Zoom Meeting ID
- 62893115044
- Host
- Graeme A Stewart
- Alternative host
- Andre Sailer
- Useful links
- Join via phone
- Zoom URL
-
Software R&D Working Meeting Minutes
2024-10-16
Room: Graeme, Leonhard, Alberto, Juan, Joanna, Peter, Florine, Mateusz, Andi, André, Anna
Remote: Swathi, Joshua, Peter Hristov
News
- Seminar Presentations: Mid of '25, presentation by Tracking Reco
Slides for EP-Retreat
- Please check today or tomorrow.
Machine Learning Faster Simulation
How long does it take to do the first training?
Speed cf. Geant4?
What happened to GANs?
-
Andi - DDFastShowerML, re. ATLAS ISF, this was overdesigned and the trigger step had far too many options (topology, for example). Lots of consistency problems. In practice now only geometry is used, and a little bit of a particle triggering. Code complexity is hard to manage. Ask what is it that we really need?
-
Juan - Are other detectors than ILD supported for the di-photon benchmark. Yes.
-
Graeme - are diffusion models hitting the mark for physics performance?
- Representation of data is very good in these models
- Bring fastsim to the level where it can use the same systematics as full sim - then you hit the metric of success (reduces human load to not have to do two validations)
-
Graeme - for training, eventually the "traning from scratch" model would converge? And the training is always on the full reverse diffusion (un-distilled)
- Yes and yes
There are minutes attached to this event.
Show them.
