3 citations · 4 across the 5 of their papers we have counts for
5 papers
Generalization error bounds for two-layer neural networks with Lipschitz loss function
Jiang Yu Nguwi, Nicolas Privault
We derive generalization error bounds for the training of two-layer neural networks without assuming boundedness of the loss function, using Wasserstein distance estimates on the d…
Numerical solution of the incompressible Navier-Stokes equation by a deep branching algorithm
Jiang Yu Nguwi, Guillaume Penent, Nicolas Privault
We present an algorithm for the numerical solution of systems of fully nonlinear PDEs using stochastic coded branching trees. This approach covers functional nonlinearities involvi…
A deep learning approach to the probabilistic numerical solution of path-dependent partial differential equations
Jiang Yu Nguwi, Nicolas Privault
Recent work on Path-Dependent Partial Differential Equations (PPDEs) has shown that PPDE solutions can be approximated by a probabilistic representation, implemented in the literat…
A deep branching solver for fully nonlinear partial differential equations
Jiang Yu Nguwi, Guillaume Penent, Nicolas Privault
We present a multidimensional deep learning implementation of a stochastic branching algorithm for the numerical solution of fully nonlinear PDEs. This approach is designed to tack…
A constructive approach to existence of equilibria in time-inconsistent stochastic control problems
Jiang Yu Nguwi, Nicolas Privault
We extend the construction of equilibria for linear-quadratic and mean-variance portfolio problems available in the literature to a large class of mean-field time-inconsistent stoc…