Toward the end-to-end optimization of particle physics instruments with differentiable programming

被引：11

作者：

Dorigo T. ^{[1
,2
,24
]}

Giammanco A. ^{[1
,3
,24
]}

Vischia P. ^{[1
,3
,24
]}

Aehle M. ^{[4
]}

Bawaj M. ^{[5
]}

Boldyrev A. ^{[1
,6
]}

de Castro Manzano P. ^{[1
,2
]}

Derkach D. ^{[1
,6
]}

Donini J. ^{[1
,7
,24
]}

Edelen A. ^{[8
]}

Fanzago F. ^{[1
,2
]}

Gauger N.R. ^{[4
]}

Glaser C. ^{[1
,9
]}

Baydin A.G. ^{[1
,10
]}

Heinrich L. ^{[1
,11
]}

Keidel R. ^{[12
]}

Kieseler J. ^{[1
,13
]}

Krause C. ^{[1
,14
]}

Lagrange M. ^{[1
,3
]}

Lamparth M. ^{[1
,11
]}

Layer L. ^{[1
,2
,15
]}

Maier G. ^{[16
]}

Nardi F. ^{[1
,2
,7
,17
]}

Pettersen H.E.S. ^{[18
]}

Ramos A. ^{[19
]}

Ratnikov F. ^{[1
,6
]}

Röhrich D. ^{[20
]}

de Austri R.R. ^{[19
]}

del Árbol P.M.R. ^{[1
,21
]}

Savchenko O. ^{[2
,3
]}

Simpson N. ^{[22
]}

Strong G.C. ^{[1
,2
]}

Taliercio A. ^{[3
]}

Tosi M. ^{[1
,2
,17
]}

Ustyuzhanin A. ^{[1
,25
]}

Zaraket H. ^{[1
,23
]}

机构：

[1] Istituto Nazionale di Fisica Nucleare, Sezione di Padova

[2] Centre for Cosmology, Particle Physics and Phenomenology (CP3), Université catholique de Louvain

[3] Chair for Scientific Computing, Technische Universität Kaiserslautern

[4] Università di Perugia and INFN, Sezione di Perugia

[5] Université Clermont Auvergne, Laboratoire de Physique de Clermont

[6] Department of Physics and Astronomy, Uppsala University

[7] Department of Computer Science, University of Oxford

[8] Physik-Department, Technische Universität München

[9] Center for Technology and Transfer, University of Applied Sciences Worms

[10] NHETC, Department of Physics and Astronomy, Rutgers University

[11] Department of Oncology and Medical Physics, Haukeland University Hospital

[12] Instituto de Física Corpuscular, UV-CSIC

[13] Department of Physics and Technology, University of Bergen

[14] Instituto de Física de Cantabria, UC-CSIC

[15] Multi-Disciplinary Physics Laboratory, Optics and Fiber Optics Group, Faculty of Sciences, Lebanese University

[16] Constructor University Bremen gGmbH, Campus Ring 1, Bremen

来源：

Reviews in Physics | 2023年 / 10卷

基金：

欧盟地平线“2020”; 美国国家科学基金会;

关键词：

Astrophysics; Differentiable programming; Machine learning; Nuclear physics; Optimization; Particle detectors; Particle physics;

D O I：

10.1016/j.revip.2023.100085

中图分类号：

学科分类号：

摘要：

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. © 2023 The Author(s)

引用

共 50 条

[1] End-to-End Differentiable Physics for Learning and Control
Belbute-Peres, Filipe de A.
Smith, Kevin A.
Allen, Kelsey R.
Tenenbaum, Joshua B.
Kolter, J. Zico
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
[2] Pontryagin Differentiable Programming: An End-to-End Learning and Control Framework
Jin, Wanxin
Wang, Zhaoran
Yang, Zhuoran
Mou, Shaoshuai
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 33, NEURIPS 2020, 2020, 33
[3] Differentiable Particle Filters: End-to-End Learning with Algorithmic Priors
Jonschkowski, Rico
Rastogi, Divyam
Brock, Oliver
ROBOTICS: SCIENCE AND SYSTEMS XIV, 2018,
[4] End-to-End Differentiable Proving
Rocktaschel, Tim
Riedel, Sebastian
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30
[5] End-to-End Semi-supervised Learning for Differentiable Particle Filters
Wen, Hao
Chen, Xiongjie
Papagiannis, Georgios
Hu, Conghui
Li, Yunpeng
2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021), 2021, : 5825 - 5831
[6] End-to-End Differentiable Physics Temperature Estimation for Permanent Magnet Synchronous Motor
Wang, Pengyuan
Wang, Xinjian
Wang, Yunpeng
WORLD ELECTRIC VEHICLE JOURNAL, 2024, 15 (04):
[7] Differentiable Compound Optics and Processing Pipeline Optimization for End-to-end Camera Design
Tseng, Ethan
Mosleh, Ali
Mannan, Fahim
St-Arnaud, Karl
Sharma, Avinash
Peng, Yifan
Braun, Alexander
Nowrouzezahrai, Derek
Lalonde, Jean-Francois
Heide, Felix
ACM TRANSACTIONS ON GRAPHICS, 2021, 40 (02):
[8] End-to-End Differentiable Learning of Protein Structure
AlQuraishi, Mohammed
CELL SYSTEMS, 2019, 8 (04) : 292 - +
[9] Differentiable MPC for End-to-end Planning and Control
Amos, Brandon
Rodriguez, Ivan Dario Jimenez
Sacks, Jacob
Boots, Byron
Kolter, J. Zico
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
[10] End-to-End Differentiable Adversarial Imitation Learning
Baram, Nir
Anschel, Oron
Caspi, Itai
Mannor, Shie
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 70, 2017, 70

← 1 2 3 4 5 →