3 papers
math.OC2026
Natural Riemannian gradient for learning functional tensor networks
Nikolas Klug, Michael Ulbrich, André Uschmajew +1
We consider machine learning tasks with low-rank functional tree tensor networks (TTN) as the learning model. While in the case of least-squares regression, low-rank functional TTN…
math.OC2026
Enclosing minima in nonsmooth optimization via trust regions of higher-order cutting-plane models
Bennet Gebken, Michael Ulbrich
We propose a globally convergent trust-region bundle method for minimizing lower- functions using higher-order cutting-plane models. Under certain growth assumptions on the ob…
math.OC2026
Superlinear convergence in nonsmooth optimization via higher-order cutting-plane models
Bennet Gebken, Michael Ulbrich
A cutting-plane model for a nonsmooth function is the maximum of several first-order expansions centered at different points. Using such a model in a bundle method leads to linear…