DOE OSTI · 2923038
Generalized parton distributions from symbolic regression
Abstract
AI/ML informed Symbolic Regression is the next stage of scientific modeling. We utilize a highly customizable symbolic regression package “PySR” to model the x and t dependence of the flavor isovector combination Hu-d(x, t, ) at = 0. These PySR models were trained on GPD results provided by both Lattice QCD and phenomenological sources GGL, GK, and VGG. We demonstrate, for the first time, the consistency and systematic convergence of Symbolic Regression by quantifying the disparate models through their Taylor expansion coefficients. In addition to PySR penalizing models with higher complexity and mean-squared error, we implement schemes that test specific physics hypotheses, including force-factorized x and t dependence and Regge behavior in PySR GPDs. We show that PySR can identify factorizing GPD sources based on their response to the Force-Factorized model. Here, knowing the precise behavior of the GPDs, and their uncertainties in a wide range in x and t, crucially impacts our ability to concretely and quantitatively predict hadronic spatial distributions and their derived quantities.
Keep this discovery
Explore connections, maps & timelines
Dotson, Andrew [New Mexico State University, Las Cruces, NM (United States)], Panjsheeri, Zaki [University of Virginia, Charlottesville, VA (United States)], Singireddi, Anusha Reddi [Old Dominion University, Norfolk, VA (United States)], Adams, Douglas Q. [University of Virginia, Charlottesville, VA (United States)], Cui´c, Maria [University of Virginia, Charlottesville, VA (United States)], Ortiz-Pacheco, Emmanuel [Michigan State University, East Lansing, MI (United States)], Pandey, Saraswati [University of Virginia, Charlottesville, VA (United States)], Bo¨er, Marie [Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States)], Chern, Gia-Wei [University of Virginia, Charlottesville, VA (United States)], Engelhardt, Michael [New Mexico State University, Las Cruces, NM (United States)], Goldstein, Gary R. [Tufts University, Medford, MA (United States)], Li, Yaohang [Old Dominion University, Norfolk, VA (United States)], Lin, Huey-Wen [Michigan State University, East Lansing, MI (United States)], Liuti, Simonetta [University of Virginia, Charlottesville, VA (United States)], Sievert, Matthew D. [New Mexico State University, Las Cruces, NM (United States)]. 2026-05-26. Generalized parton distributions from symbolic regression. https://doi.org/10.1103/ynm6-znr4
Cite the original work for its findings. Save a collection to share your selection of sources.