3 papers
cs.LG2025
Towards an Optimal Control Perspective of ResNet Training
Jens Püttschneider, Simon Heilig, Asja Fischer +1
We propose a training formulation for ResNets reflecting an optimal control problem that is applicable for standard architectures and general loss functions. We suggest bridging bo…
eess.SY2025
Towards Event-Triggered NMPC for Efficient 6G Communications: Experimental Results and Open Problems
Jens Püttschneider, Julian Golembiewski, Niklas A. Wagner +2
Networked control systems enable real-time control and coordination of distributed systems, leveraging the low latency, high reliability, and massive connectivity offered by 5G and…
cs.LG2024
On Dissipativity of Cross-Entropy Loss in Training ResNets
Jens Püttschneider, Timm Faulwasser
The training of ResNets and neural ODEs can be formulated and analyzed from the perspective of optimal control. This paper proposes a dissipative formulation of the training of Res…