A deterministic McKean-Pontryagin minimum principle is formulated for stochastic optimal control via auxiliary functions that enable Hamiltonian structure and time-decoupling.
Gottwald, Shuigen Liu, Youssef Marzouk, Sebas tian Reich, and Xin T
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
FPPF uses a learned conditional generative proposal approximating the optimal proposal in particle filters, with tractable likelihoods for Bayesian updates and localization for high dimensions, outperforming baselines on nonlinear non-Gaussian systems.
The authors derive forward mean-field equations that integrate ensemble Kalman filtering with McKean-Pontryagin control to enable simultaneous online data assimilation and optimal control for partially observed stochastic systems, with numerical tests on Lorenz-63, Lorenz-96, and an inverted-pendul
Introduces a sequential forward-backward diffusion framework that generates adapted time series by conditioning on prior history, with a parallelizable score-matching objective and statistical guarantees for ReLU networks.
citing papers explorer
-
On a mean-field Pontryagin minimum principle for stochastic optimal control
A deterministic McKean-Pontryagin minimum principle is formulated for stochastic optimal control via auxiliary functions that enable Hamiltonian structure and time-decoupling.
-
Generative Model Proposal based Particle Filtering for Data Assimilation
FPPF uses a learned conditional generative proposal approximating the optimal proposal in particle filters, with tractable likelihoods for Bayesian updates and localization for high dimensions, outperforming baselines on nonlinear non-Gaussian systems.
-
Digital Twins: McKean-Pontryagin Control for Partially Observed Physical Twins
The authors derive forward mean-field equations that integrate ensemble Kalman filtering with McKean-Pontryagin control to enable simultaneous online data assimilation and optimal control for partially observed stochastic systems, with numerical tests on Lorenz-63, Lorenz-96, and an inverted-pendul
-
Diffusion Models for Adaptive Sequential Data Generation
Introduces a sequential forward-backward diffusion framework that generates adapted time series by conditioning on prior history, with a parallelizable score-matching objective and statistical guarantees for ReLU networks.