MODE (for Machine-learning Optimized Design of Experiments) is a nascent collaboration of physicists and computer scientists who target the use of differentiable programming in design optimization of detectors for particle physics applications, extending from fundamental research at accelerators, in space, and in nuclear physics and neutrino facilities, to industrial applications employing the technology of radiation detection.
We aim to develop a modular, customizable, and scalable, fully differentiable pipeline for the end-to-end optimization of articulated objective functions that model in full the true goals of experimental particle physics endeavours, to ensure optimal detector performance, analysis potential, and cost-effectiveness.
The main goal of our activities is to develop an architecture that can be adapted to the above use cases but will also be customizable to any other experimental endeavour employing particle detection at its core. We welcome suggestions, as well as interest in joining our effort, by researchers focusing on use cases for which this technology can be of benefit.
The above program has been submitted in a concise form as an expression of interest
to the JENAA group
Below is a concise list of relevant publications to the research interests of the MODE collaboration:
- A. Gunes Baydin, B.A. Pearlmutter, A.A. Radul, and J.M. Siskind, "Automatic Differentiation in Machine Learning: a Survey", Journal of Machine Learning Research (JMLR) 18 (153) (2018) 1, http://jmlr.org/papers/v18/17-468.html
- T. Dorigo, "Geometry Optimization of a Muon-Electron Scattering Detector," Physics Open 4 (2020) 100022, arXiv:200200973[physics.ins-det], doi: 10.1016/j.physo.2020.100022.
- T. Dorigo, J. Kieseler, L. Layer and G. Strong, "Muon Energy Measurement from Radiative Losses in a Calorimeter for a Collider Detector", http://arxiv.org/abs/2008.10958 [physics.ins-det] (2020).
- S. Shirobokov, A. Ustyuzhanin, A. Gunes Badyin et al., "Differentiating the Black-Box: Optimization with Local Generative Surrogates", arXiv:2002.04632v1 [cs.LG] (2020).
- K. Cranmer, J. Brehmer, and G. Louppe, "The frontier of simulation-based inference", arXiv:1911.01429[stat.ML] (2019), Proceedings of the National Academy of Sciences.
- F. Ratnikov, "Using machine learning to speed up and improve calorimeter R&D", JINST 15 (2020) C05032, doi: 10.1088/1748-0221/15/05/C05032.
- F. Ratnikov, D. Derkach, A. Boldyrev, A. Shevelev, P. Fakanov, L. Matyushin, "Using machine learning to speed up new and upgrade detector studies: a calorimeter case", to appear in proceedings of CHEP 2019, https://arxiv.org/abs/2003.05118
- A. Boldyrev, D. Derkach, F. Ratnikov, A. Shevelev, "ML-assisted versatile approach to Calorimeter R&D", https://arxiv.org/abs/2005.07700
- P. Giubilato et al., "iMPACT: innovative pCT scanner", IEEE Nucl. Science Symposium and Medical Imaging Conference (NSS/MIC) IEEE (2015), https://ieeexplore.ieee.org/abstract/document/7581240.
- S. Wuyckens, A. Giammanco, P. Demin, and E. Cortina Gil, "A Portable muon telescope based on small and gas-tight Resistive Plate Chambers"<, Phil. Trans. Royal Soc. A377 (2019) 2137, arXiv:1806.06602v2[physics.ins-det] (2018), doi: 10.1098/rsta.2018.0139.
- J. Kieseler, "Object condensation: one-stage grid-free multi-object reconstruction in physics detectors, graph and image data", arXiv:2002.03605[physics.data-an] (2020).
- P. de Castro Manzano and T. Dorigo, "INFERNO: Inference-Aware Neural Optimization", Comp. Phys. Commun. 244 (2019) 170; Arxiv:1806.04743v2 [stat.ml] (2018), doi: 10.1016/j.cpc.2019.06.007 .
- J. Brehmer, K. Cranmer et al., "MadMiner: Machine learning-based inference for particle physics", Comput. Softw. Big Sci. 4 (2020) 1, 3, doi: 10.1007/s41781-020-0035-2.
- G. Louppe, J. Hermans, and K. Cranmer, "Adversarial Variational Optimization of Non-Differentiable Simulators", PMLR 89:1438-1447, 2019, arXiv:1707.07113[stat.ML].
- K. Cranmer, J. Pavez, and G. Louppe, "Approximating Likelihood Ratios with Calibrated Discriminative Classifiers", arXiv:1506.02169[stat.ML] (2015).