AI-assisted design of experiments at the frontiers of computation: methods and new perspectives

TL;DR

This paper explores AI-assisted experimental design for high-dimensional physics experiments, highlighting gradient-based optimization and neuromorphic hardware to address computational challenges and enable advanced collider research.

Contribution

It introduces the first proofs-of-concept for gradient-based optimization and neuromorphic hardware implementations in experimental design for high-energy physics.

Findings

Proof-of-concept for gradient-based optimization in experimental design

Implementation of neuromorphic hardware architectures for this purpose

Potential to scale up to complex collider experiments

Abstract

Designing the next generation colliders and detectors involves solving optimization problems in high-dimensional spaces where the optimal solutions may nest in regions that even a team of expert humans would not explore. Resorting to Artificial Intelligence to assist the experimental design introduces however significant computational challenges in terms of generation and processing of the data required to perform such optimizations: from the software point of view, differentiable programming makes the exploration of such spaces with gradient descent feasible; from the hardware point of view, the complexity of the resulting models and their optimization is prohibitive. To scale up to the complexity of the typical HEP collider experiment, a change in paradigma is required. In this contribution I will describe the first proofs-of-concept of gradient-based optimization of experimental design and implementations in neuromorphic hardware architectures, paving the way to more complex challenges.