Toward the End-to-End Optimization of Particle Physics Instruments with Differentiable Programming: a White Paper

Abstract

The full optimization of the design and operation of instruments whose functioning relies on the interaction of radiation with matter is a superhuman task, given the large dimensionality of the space of possible choices for geometry, detection technology, materials, data-acquisition, and informationextraction 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 by means of 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 document 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.

Novel machine learning and differentiable programming techniques applied to the VIP-2 underground experiment

“…Differentiable programming is a computational paradigm that enables the automatic differentiation of mathematical functions, making it a valuable tool for scientific computing and ML, already pioneered in High Energy Physics [11][12][13]. Within this paradigm, it is possible to employ high-level syntax to form fully differentiable complex models that can be optimized using gradient-based methods.…”

“…[6][7][8][9][10]), however, the calibration of detectors array in conditions of sparse data is still a challenging task. While some applications have pioneered the use of differentiable ML pipelines for detector optimization [11][12][13], so far none of them have addressed the issue of detector calibration.…”