Alladi Ramakrishnan Hall

Advancing Precision Higgs and Top Physics: Effective Field Theory and Machine Learning Synergies

Akanksha Bhardwaj

Oklahoma State University

In this talk, we explore the application of Graph Neural Networks (GNNs) to constrain SMEFT operators in pp→ttˉ production. By utilizing GNNs to process multidimensional phase space data, we demonstrate significant improvements over traditional cut-based analyses in extracting operator coefficients from collider data, highlighting the advantages of machine learning in precision phenomenology.

We also present a machine learning-driven approach to design CP-odd observables for the Higgs sector, achieving enhanced sensitivity to CP-violating effects compared to traditional angular observables. Finally, we probe sources of non-linear CP-violation in the Higgs Effective Field Theory (HEFT) framework, focusing on single and double Higgs production processes and distinguishing HEFT predictions from SMEFT signatures. This work underscores the synergy between machine learning and effective field theories in advancing precision Higgs physics.