5 papers
Pathwise Learning of Stochastic Dynamical Systems with Partial Observations
Nicole Tianjiao Yang
The reconstruction and inference of stochastic dynamical systems from data is a fundamental task in inverse problems and statistical learning. While surrogate modeling advances com…
Mixed Precision Training of Neural ODEs
Elena Celledoni, Brynjulf Owren, Lars Ruthotto +1
Exploiting low-precision computations has become a standard strategy in deep learning to address the growing computational costs imposed by ever larger models and datasets. However…
On the Convergence of Jacobian-Free Backpropagation for Optimal Control Problems with Implicit Hamiltonians
Eric Gelphman, Deepanshu Verma, Nicole Tianjiao Yang +2
Optimal feedback control with implicit Hamiltonians poses a fundamental challenge for learning-based value function methods due to the absence of closed-form optimal control laws.…
End-to-End Training of High-Dimensional Optimal Control with Implicit Hamiltonians via Jacobian-Free Backpropagation
Eric Gelphman, Deepanshu Verma, Nicole Tianjiao Yang +2
Neural network approaches that parameterize value functions have succeeded in approximating high-dimensional optimal feedback controllers when the Hamiltonian admits explicit formu…
When are dynamical systems learned from time series data statistically accurate?
Jeongjin Park, Nicole Yang, Nisha Chandramoorthy
Conventional notions of generalization often fail to describe the ability of learned models to capture meaningful information from dynamical data. A neural network that learns comp…