2 papers
math.OC2026
Mirror Descent for Deterministic Optimal Control
Ye Feng, Jianfeng Lu
We study an explicit mirror-descent method for finite-horizon deterministic optimal control problems. The method is motivated by Pontryagin's maximum principle: at each iteration,…
math.OC2026
State-space models through the lens of ensemble control
Ye Feng, Jianfeng Lu
State-space models (SSMs) are effective architectures for sequential modeling, but a rigorous theoretical understanding of their training dynamics is still lacking. In this work, w…