Uncovering Singularities in Feynman Integrals via Machine Learning
This provides a versatile tool for exploring scattering amplitudes and opens new avenues for multi-loop amplitude analysis in theoretical physics.
The paper tackles the problem of extracting the full symbol alphabet of multi-loop Feynman integrals by introducing a machine-learning framework based on symbolic regression, successfully reconstructing complete symbol alphabets in nontrivial examples with demonstrated robustness and generality.
We introduce a machine-learning framework based on symbolic regression to extract the full symbol alphabet of multi-loop Feynman integrals. By targeting the analytic structure rather than reduction, the method is broadly applicable and interpretable across different families of integrals. It successfully reconstructs complete symbol alphabets in nontrivial examples, demonstrating both robustness and generality. Beyond accelerating computations case by case, it uncovers the analytic structure universally. This framework opens new avenues for multi-loop amplitude analysis and provides a versatile tool for exploring scattering amplitudes.