A gradient-enhanced functional tensor train cross approximation method for the resolution of
the Hamilton–Jacobi–Bellman (HJB) equations associated with optimal feedback control of …

We consider a stochastic optimal exit time feedback control problem. The Bellman equation
is solved approximatively via the Policy Iteration algorithm on a polynomial ansatz space by …

We present a novel method to approximate optimal feedback laws for nonlinear optimal
control based on low‐rank tensor train (TT) decompositions. The approach is based on the …

Approximation of high dimensional functions is in the focus of machine learning and data-
based scientific computing. In many applications, empirical risk minimisation techniques …

We consider high-dimensional, non-linear functional equations. These functional equations
are mostly the Bellman equation known from optimal control or related fields. Within this …

This work proposes a novel numerical scheme for solving the high-dimensional Hamilton-
Jacobi-Bellman equation with a functional hierarchical tensor ansatz. We consider the …

This thesis considers the problem of approximating low-rank tensors from data and its use
for the non-intrusive solution of certain high-dimensional parametric partial differential …

This thesis centers on the development of novel algorithms for Machine Learning (ML),
Optimal Control (OC) and SDE-based sampling using low rank Tensor Trains (TT). First, a …