Choose timezone
Your profile timezone:
LPCC Fast Detector Simulation Workshop
→
Europe/Zurich
Alberto Ribon
(CERN),
Anna Zaborowska
(CERN),
Witold Pokorski
(CERN)
Description
The goal of the workshop is to discuss the developments of the fast detector simulation and to identify common interests with room for collaboration. The workshop has been divided into 6 sessions to facilitate the discussions on the topic in focus. Please find the list of useful questions around the topic in the description of each session in the timetable.
The Workshop will be held in remote mode only.
Participants
105
View full list
-
- 15:00 → 15:05
-
15:05
→
16:00
Fast Simulation applicability and accuracy¶
How is fast simulation used: applied to which detectors? Are there specific “sensitive” parts of the detector where it is difficult to get fast simulation? Is it used widely in production? Which physics analyses can use fast simulation, which cannot? What are the demands on the accuracy of the (fast) simulation? Do you/can you tune fast simulation to collision data to get better results than from the full simulation?
How does it look now, but also how it changes for Run3 & HL-LHC?
-
15:05
Session: Applicability and accuracy
Speaker: Samuel Louis Bein (Hamburg University (DE)) -
15:15
Session: Applicability and accuracy
Speakers: Joshua Falco Beirer (Georg August Universitaet Goettingen (DE)), Joshua Falco Beirer (CERN, Georg-August-Universitaet Goettingen (DE)), Joshua Falco Beirer (Georg August Universitaet Goettingen (DE)) -
15:25
Session: Applicability and accuracy
Speaker: Roberto Preghenella (INFN, Bologna (IT)) -
15:35
Session: Applicability and accuracy
Speaker: Constantine Chimpoesh -
15:45
-
15:05
-
16:00
→
16:55
Data preprocessing¶
Which particle types and properties (energy, angle) are considered?
How large is the full sim dataset used to extract parametrization/train the network? Is the dataset balanced (is the number of events for the different particle properties almost the same?)
How the structure of the input data is defined (hits, cells, clusters, custom voxels,..)?
Which data structure is used for the ML training (1D vector, images, graphs..)?
Is input data scaled? How?
How do you store the preprocessed data?
How are the condition values for the ML training (energy of the particle, angle,..) encoded?-
16:00
Session: Data preprocessing
Speaker: Saverio Mariani (Universita e INFN, Firenze (IT)) -
16:10
Session: Data preprocessing
Speaker: Moritz Scham (Deutsches Elektronen-Synchrotron (DE)) -
16:20
Session: Data preprocessing
Speaker: Michele Faucci Giannelli (INFN e Universita Roma Tor Vergata (IT)) -
16:30
Session: Data preprocessing
Speaker: Jan Michal Dubinski (Warsaw University of Technology (PL)) -
16:40
-
16:00
-
16:55
→
17:10
Break 15m
-
17:10
→
18:00
Tuning¶
How the extraction and tuning of parameters for the fast simulation are done?
For ML, how training is performed? What hyperparameter tuning approach is adopted? What metric is used to compare the performance of the model during the tuning process?-
17:10
Session: Tuning
Speaker: Michele Faucci Giannelli (INFN e Universita Roma Tor Vergata (IT)) -
17:20
Session: Tuning
Speaker: Jan Michal Dubinski (Warsaw University of Technology (PL)) -
17:30
Session: Tuning
Speaker: Matteo Barbetti (Universita e INFN, Firenze (IT)) -
17:40
Session: Tuning
Speaker: Moritz Jonas Wolf (Hamburg University (DE)) -
17:50
-
17:10
-
18:00
→
19:00
Further discussions 1h
In case we need more time.
-
-
15:00
→
15:55
Validation¶
How do you validate fast simulation?
Is it on e.g. particle shower characteristics (longitudinal/transverse profiles, etc.), on high-level results of physics analyses, ...?
For ML, what is the metric used to validate the model and what is the objective function you are optimizing during the training?-
15:00
Session: Validation
Speaker: Kamil Rafal Deja (Warsaw University of Technology (PL)) -
15:10
Session: Validation
Speaker: Lucio Anderlini (Universita e INFN, Firenze (IT)) -
15:20
Session: Validation
Speaker: Debajyoti Sengupta (Universite de Geneve (CH)) -
15:30
Session: Validation
Speaker: Raghav Kansal (Univ. of California San Diego (US)) -
15:40
-
15:00
-
15:55
→
16:50
Fast sim model integration¶
How is fast simulation integrated into the experiment's framework?
How is the model stored (file format, size, ...)? Are there any specific files to store in addition to the model?
For ML, which inference library is used?
How much time does it take to generate one event?
What is the memory footprint?
Are there any optimization approaches considered to reduce the memory?
Has the ML simulation been tested on GPU?-
15:55
Session: Integration
Speaker: Michele Faucci Giannelli (INFN e Universita Roma Tor Vergata (IT)) - 16:05
-
16:15
Session: Integration
Speaker: Kevin Pedro (Fermi National Accelerator Lab. (US)) -
16:25
Session: Integration
Speaker: Kamil Rafal Deja (Warsaw University of Technology (PL)) - 16:35
-
16:45
-
15:55
-
16:50
→
17:10
Break 20m
-
17:10
→
18:05
Reusability and Generalisation¶
Are there any valuable lessons to be learnt by others?
Tools that can be reused?
Maybe some ideas have failed for your detectors (or parts of it) and it can be useful to others?
What are your plans, maybe there is room for collaboration?-
17:10
Session: Reusability & Generalization
Speaker: Adam Davis (University of Manchester (GB)) -
17:20
Session: Reusability & Generalization
Speaker: Erik Buhmann (Hamburg University (DE)) -
17:30
Session: Reusability & Generalization
Speaker: Kamil Rafal Deja (Warsaw University of Technology (PL)) -
17:40
Session: Reusability & Generalization
Speaker: Michele Faucci Giannelli (INFN e Universita Roma Tor Vergata (IT)) -
17:50
Session: Reusability & Generalization
Speaker: Dalila Salamani (CERN) -
18:00
-
17:10
-
18:05
→
19:00
Further discussions 55m
In case we need more time.
-
15:00
→
15:55
