Title: Learning the Language of Scattering Amplitudes
Abstract: Machine learning (ML) has grown dramatically in high-energy physics in recent years. Tasks such as classification, regression, anomaly detection, and density estimation now benefit from modern ML approaches that often outperform traditional baselines. Far less attention, however, has gone to the theoretical side, even though (symbolic) data is plentiful. In this talk, I will discuss how modern models can help bridge this gap and “learn the language” of scattering amplitudes. In particular, I will describe recent work on simplifying amplitude expressions, reconstructing S-matrix phases, and recovering exact analytic formulas.
For help, please contact Webmaster.