2 papers
math.NA2024
Algebraic Conditions for Stability in Runge-Kutta Methods and Their Certification via Semidefinite Programming
Austin Juhl, David Shirokoff
In this work, we present approaches to rigorously certify - and -stability in Runge-Kutta methods through the solution of convex feasibility problems defined by linear mat…
cs.LG2024
Continuous Mean-Zero Disagreement-Regularized Imitation Learning (CMZ-DRIL)
Noah Ford, Ryan W. Gardner, Austin Juhl +1
Machine-learning paradigms such as imitation learning and reinforcement learning can generate highly performant agents in a variety of complex environments. However, commonly used…