3 papers
cs.LG2025
Enabling Automatic Differentiation with Mollified Graph Neural Operators
Ryan Y. Lin, Julius Berner, Valentin Duruisseaux +5
Physics-informed neural operators offer a powerful framework for learning solution operators of partial differential equations (PDEs) by combining data and physics losses. However,…
math.AP2025
An Analysis of the Riemann Problem for a System of Keyfitz-Kranzer Type Balance Laws With a Time-Dependent Source Term
Josh Culver, Aubrey Ayres, Evan Halloran +3
We consider a system consisting of one conservation law and one balance law with a time-dependent source term, and provide a comprehensive analysis of Riemann solutions, including…
math.AP2025
An Analysis of the Riemann Problem for a System of Keyfitz-Kranzer Type Conservation Laws Using Shadow Waves and Dafermos Regularization
Josh Culver, Aubrey Ayres, Evan Halloran +3
We consider a system of two conservation laws and provide a detailed description of both classical and non-classical self-similar Riemann solutions. In particular, we demonstrate t…