AI-Driven Discovery of Information-Efficient Collider Observables for Interference Measurements
Jiahui Lin, Yandong Liu

TL;DR
This paper introduces an AI-driven symbolic evolution method to discover interpretable collider observables that efficiently probe interference effects, outperforming standard angular analyses in retaining Fisher information.
Contribution
The work presents a novel approach to automatically discover compact, interpretable observables for collider interference measurements using AI and symbolic evolution.
Findings
Discovered observables retain more Fisher information than standard methods.
Revealed characteristic helicity-interference harmonics in the learned expressions.
Identified laboratory-frame asymmetries and angular kernels as key components.
Abstract
Optimal observables provide statistically powerful probes of small deformations from a reference theory, but in realistic collider measurements they are rarely available in compact analytic form. We show that interpretable event-level observables can be discovered by AI-driven symbolic evolution using score information from matrix-element reweighting as the statistical target. Focusing on the CP-sensitive interaction , we study two complementary realizations of the same coupling structure: associated production and the decay channel . The learned observables retain substantially more local Fisher information than standard angular baselines while remaining compact analytic functions. In both cases, the discovered expressions recover characteristic helicity-interference harmonics. In…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
