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

被引：15

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

[21] DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs
Sadeghian, Ali
Armandpour, Mohammadreza
Ding, Patrick
Wang, Daisy Zhe
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
[22] End-to-end differentiable construction of molecular mechanics force fields
Wang, Yuanqing
Fass, Josh
Kaminow, Benjamin
Herr, John E.
Rufa, Dominic
Zhang, Ivy
Pulido, Ivan
Henry, Mike
Macdonald, Hannah E. Bruce
Takaba, Kenichiro
Chodera, John D.
CHEMICAL SCIENCE, 2022, 13 (41) : 12016 - 12033
[23] End-to-end automatic lens design with a differentiable diffraction model
Zhang, Wenguan
Ren, Zheng
Hou, Jingwen
Hen, Shiqi
Feng, Huajun
Li, Q., I
Xu, Zhihai
Chen, Yueting
OPTICS EXPRESS, 2024, 32 (25): : 44328 - 44345
[24] End-to-End Complex Lens Design with Differentiable Ray Tracing
Sun, Qilin
Wang, Congli
Fu, Qiang
Dun, Xiong
Heidrich, Wolfgang
ACM TRANSACTIONS ON GRAPHICS, 2021, 40 (04):
[25] ∂PV: An End-to-End Differentiable Solar-Cell Simulator
Mann, Sean
Fadel, Eric
Schoenholz, Samuel S.
Cubuk, Ekin D.
Johnson, Steven G.
Romano, Giuseppe
Mann, Sean (seanmann@mit.edu); Romano, Giuseppe (romanog@mit.edu), 2021, arXiv
[26] End-to-End Differentiable Model for Optimization of Rocket-Powered Vehicles Including Plume Radiant Emission
Mathesius, Kelly J.
Sharpe, Peter D.
Hansman, R. John
JOURNAL OF SPACECRAFT AND ROCKETS, 2024,
[27] End-to-End Optimization of Constellation Shaping for Wiener Phase Noise Channels With a Differentiable Blind Phase Search
Rode, Andrej
Geiger, Benedikt
Chimmalgi, Shrinivas
Schmalen, Laurent
JOURNAL OF LIGHTWAVE TECHNOLOGY, 2023, 41 (12) : 3849 - 3859
[28] End-to-End Optimization of Scene Layout
Luo, Andrew
Zhang, Zhoutong
Wu, Jiajun
Tenenbaum, Joshua B.
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, : 3753 - 3762
[29] End-to-end Conditional Robust Optimization
Chenreddy, Abhilash Reddy
Delage, Erick
UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, 2024, 244 : 736 - 748
[30] End-to-end optimization of prosthetic vision
van Steveninck, Jaap de Ruyter
Guclu, Umut
van wezel, Richard
van Gerven, Marcel
JOURNAL OF VISION, 2022, 22 (02):

← 1 2 3 4 5 →