activity
20152026
most citedError bounds for maxout neural network approximations of model predictive control

6 citations · 41 across the 34 of their papers we have counts for

collaborators
Showing 2023Show all

5 papers · 1 filter

eess.SY2023

On the security of randomly transformed quadratic programs for privacy-preserving cloud-based control

Philipp Binfet, Nils Schlüter, Moritz Schulze Darup

Control related data, such as system states and inputs or controller specifications, is often sensitive. Meanwhile, the increasing connectivity of cloud-based or networked control…

math.OC2023★ 2 cited

Efficient computation of Lipschitz constants for MPC with symmetries

Dieter Teichrib, Moritz Schulze Darup

Lipschitz constants for linear MPC are useful for certifying inherent robustness against unmodeled disturbances or robustness for neural network-based approximations of the control…

eess.SY2023★ 6 cited

Error bounds for maxout neural network approximations of model predictive control

Dieter Teichrib, Moritz Schulze Darup

Neural network (NN) approximations of model predictive control (MPC) are a versatile approach if the online solution of the underlying optimal control problem (OCP) is too demandin…

cs.CR2023

Cryptanalysis of Random Affine Transformations for Encrypted Control

Nils Schlüter, Philipp Binfet, Moritz Schulze Darup

Cloud-based and distributed computations are of growing interest in modern control systems. However, these technologies require performing computations on not necessarily trustwort…

eess.SY2023

Convex NMPC reformulations for a special class of nonlinear multi-input systems with application to rank-one bilinear networks

Manuel Klädtke, Moritz Schulze Darup

We show that a special class of (nonconvex) NMPC problems admits an exact solution by reformulating them as a finite number of convex subproblems, extending previous results to the…