A Globally Convergent Algorithm for Neural Network Parameter Optimization Based on Difference-of-Convex Functions

1 code implementation • 15 Jan 2024 • Daniel Tschernutter, Mathias Kraus, Stefan Feuerriegel

Furthermore, we mathematically analyze the convergence rate of parameters and the convergence rate in value (i. e., the training loss).

Interpretable Off-Policy Learning via Hyperbox Search

1 code implementation • 4 Mar 2022 • Daniel Tschernutter, Tobias Hatt, Stefan Feuerriegel

Using a simulation study, we demonstrate that our algorithm outperforms state-of-the-art methods from interpretable off-policy learning in terms of regret.

Generalizing Off-Policy Learning under Sample Selection Bias

no code implementations • 2 Dec 2021 • Tobias Hatt, Daniel Tschernutter, Stefan Feuerriegel

Since training data is often not representative of the target population, standard policy learning methods may yield policies that do not generalize target population.

Selection bias