collaborators

6 papers

physics.flu-dyn2026

Data-informed lifting line theory

Arjun Sharma, Jonas A. Actor, Peter A. Bosler

We present a data-driven framework that extends the predictive capability of classical lifting-line theory (LLT) to a wider aerodynamic regime by incorporating higher-fidelity aero…

cs.LG2026

Multilevel Training for Kolmogorov Arnold Networks

Ben S. Southworth, Jonas A. Actor, Graham Harper +1

Algorithmic speedup of training common neural architectures is made difficult by the lack of structure guaranteed by the function compositions inherent to such networks. In contras…

cs.LG2026

Discovery of Probabilistic Dirichlet-to-Neumann Maps on Graphs

Adrienne M. Propp, Jonas A. Actor, Elise Walker +3

Dirichlet-to-Neumann maps enable the coupling of multiphysics simulations across computational subdomains by ensuring continuity of state variables and fluxes at artificial interfa…

cs.LG2025

Deriving Transformer Architectures as Implicit Multinomial Regression

Jonas A. Actor, Anthony Gruber, Eric C. Cyr

While attention has been empirically shown to improve model performance, it lacks a rigorous mathematical justification. This short paper establishes a novel connection between att…

cs.LG2025

Leveraging KANs for Expedient Training of Multichannel MLPs via Preconditioning and Geometric Refinement

Jonas A. Actor, Graham Harper, Ben Southworth +1

Multilayer perceptrons (MLPs) are a workhorse machine learning architecture, used in a variety of modern deep learning frameworks. However, recently Kolmogorov-Arnold Networks (KAN…

cs.LG2025

Mixture of neural operator experts for learning boundary conditions and model selection

Dwyer Deighan, Jonas A. Actor, Ravi G. Patel

While Fourier-based neural operators are best suited to learning mappings between functions on periodic domains, several works have introduced techniques for incorporating non triv…