Toward the end-to-end optimization of particle physics instruments with differentiable programming
(2023) In Reviews in Physics 10.- Abstract
The full optimization of the design and operation of instruments whose functioning relies on the interaction of radiation with matter is a super-human task, due to the large dimensionality of the space of possible choices for geometry, detection technology, materials, data-acquisition, and information-extraction techniques, and the interdependence of the related parameters. On the other hand, massive potential gains in performance over standard, “experience-driven” layouts are in principle within our reach if an objective function fully aligned with the final goals of the instrument is maximized through a systematic search of the configuration space. The stochastic nature of the involved quantum processes make the modeling of these... (More)
The full optimization of the design and operation of instruments whose functioning relies on the interaction of radiation with matter is a super-human task, due to the large dimensionality of the space of possible choices for geometry, detection technology, materials, data-acquisition, and information-extraction techniques, and the interdependence of the related parameters. On the other hand, massive potential gains in performance over standard, “experience-driven” layouts are in principle within our reach if an objective function fully aligned with the final goals of the instrument is maximized through a systematic search of the configuration space. The stochastic nature of the involved quantum processes make the modeling of these systems an intractable problem from a classical statistics point of view, yet the construction of a fully differentiable pipeline and the use of deep learning techniques may allow the simultaneous optimization of all design parameters. In this white paper, we lay down our plans for the design of a modular and versatile modeling tool for the end-to-end optimization of complex instruments for particle physics experiments as well as industrial and medical applications that share the detection of radiation as their basic ingredient. We consider a selected set of use cases to highlight the specific needs of different applications.
(Less)
- author
- organization
- publishing date
- 2023
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Astrophysics, Differentiable programming, Machine learning, Nuclear physics, Optimization, Particle detectors, Particle physics
- in
- Reviews in Physics
- volume
- 10
- article number
- 100085
- publisher
- Elsevier
- external identifiers
-
- scopus:85162813150
- ISSN
- 2405-4283
- DOI
- 10.1016/j.revip.2023.100085
- language
- English
- LU publication?
- yes
- id
- 3b75bb0b-1a30-482c-ae12-1e676a2973a8
- date added to LUP
- 2023-09-18 13:20:01
- date last changed
- 2023-12-06 07:26:30
@article{3b75bb0b-1a30-482c-ae12-1e676a2973a8, abstract = {{<p>The full optimization of the design and operation of instruments whose functioning relies on the interaction of radiation with matter is a super-human task, due to the large dimensionality of the space of possible choices for geometry, detection technology, materials, data-acquisition, and information-extraction techniques, and the interdependence of the related parameters. On the other hand, massive potential gains in performance over standard, “experience-driven” layouts are in principle within our reach if an objective function fully aligned with the final goals of the instrument is maximized through a systematic search of the configuration space. The stochastic nature of the involved quantum processes make the modeling of these systems an intractable problem from a classical statistics point of view, yet the construction of a fully differentiable pipeline and the use of deep learning techniques may allow the simultaneous optimization of all design parameters. In this white paper, we lay down our plans for the design of a modular and versatile modeling tool for the end-to-end optimization of complex instruments for particle physics experiments as well as industrial and medical applications that share the detection of radiation as their basic ingredient. We consider a selected set of use cases to highlight the specific needs of different applications.</p>}}, author = {{Dorigo, Tommaso and Giammanco, Andrea and Vischia, Pietro and Aehle, Max and Bawaj, Mateusz and Boldyrev, Alexey and de Castro Manzano, Pablo and Derkach, Denis and Donini, Julien and Edelen, Auralee and Fanzago, Federica and Gauger, Nicolas R. and Glaser, Christian and Baydin, Atılım G. and Heinrich, Lukas and Keidel, Ralf and Kieseler, Jan and Krause, Claudius and Lagrange, Maxime and Lamparth, Max and Layer, Lukas and Maier, Gernot and Nardi, Federico and Pettersen, Helge E.S. and Ramos, Alberto and Ratnikov, Fedor and Röhrich, Dieter and de Austri, Roberto Ruiz and del Árbol, Pablo Martínez Ruiz and Savchenko, Oleg and Simpson, Nathan and Strong, Giles C. and Taliercio, Angela and Tosi, Mia and Ustyuzhanin, Andrey and Zaraket, Haitham}}, issn = {{2405-4283}}, keywords = {{Astrophysics; Differentiable programming; Machine learning; Nuclear physics; Optimization; Particle detectors; Particle physics}}, language = {{eng}}, publisher = {{Elsevier}}, series = {{Reviews in Physics}}, title = {{Toward the end-to-end optimization of particle physics instruments with differentiable programming}}, url = {{http://dx.doi.org/10.1016/j.revip.2023.100085}}, doi = {{10.1016/j.revip.2023.100085}}, volume = {{10}}, year = {{2023}}, }