Speaker
Description
Uncertainty quantification (UQ) plays a crucial role in the predictive power of nonperturbative quantum correlation functions at high precision. My research explores novel approaches to UQ in the context of parton distribution functions (PDFs), using machine learning techniques to map observables to underlying theoretical models and to navigate the complex parametric landscape of phenomenological scenarios, including the vast ecosystem of beyond-the-Standard-Model (BSM) configurations. By leveraging variational autoencoders (VAEs) and contrastive learning with similarity metrics, I investigate how the inherent uncertainties in phenomenological extractions of collinear PDFs impact the landscape of new physics models. My approach integrates explainability methods to trace underlying theory assumptions back to the input feature space - specifically the x-dependence of PDFs - thereby identifying the salient features that shape constraints and model interpretations. This work aims to enhance the incorporation of lattice inputs in phenomenological fits and refine our understanding of nonperturbative QCD through next-generation machine learning models, ultimately pushing the frontier of particle physics discovery at future collider facilities such as the EIC.
