4 citations · 5 across the 11 of their papers we have counts for
14 papers
Stochastic Gradient Descent with Momentum: Analysis and Synthesis via Integral Quadratic Constraints
Dennis Gramlich, Carsten W. Scherer, Christian Ebenbauer
This article applies dynamic integral quadratic constraints (IQCs) to the analysis and synthesis of accelerated stochastic gradient algorithms. We consider composite objective func…
Distributionally robust LMI synthesis for LTI systems
Dennis Gramlich, Shuhao Yan, Carsten W. Scherer +1
This article shows that distributionally robust controller synthesis as investigated in \cite{taskesen2024distributionally} can be formulated as a convex linear matrix inequality (…
Lipschitz constant estimation for general neural network architectures using control tools
Patricia Pauli, Dennis Gramlich, Frank Allgöwer
This paper is devoted to the estimation of the Lipschitz constant of general neural network architectures using semidefinite programming. For this purpose, we interpret neural netw…
On moment relaxations for linear state feedback controller synthesis with non-convex quadratic costs and constraints
Dennis Gramlich, Sheng Gao, Hao Zhang +2
We present a simple and effective way to account for non-convex costs and constraints~in~state feedback synthesis, and an interpretation for the variables in which state feedback s…
State space representations of the Roesser type for convolutional layers
Patricia Pauli, Dennis Gramlich, Frank Allgöwer
From the perspective of control theory, convolutional layers (of neural networks) are 2-D (or N-D) linear time-invariant dynamical systems. The usual representation of convolutiona…
Synthesis of constrained robust feedback policies and model predictive control
Dennis Gramlich, Carsten W. Scherer, Hannah Häring +1
In this work, we develop a method based on robust control techniques to synthesize robust time-varying state-feedback policies for finite, infinite, and receding horizon control pr…
A structure exploiting SDP solver for robust controller synthesis
Dennis Gramlich, Tobias Holicki, Carsten W. Scherer +1
In this paper, we revisit structure exploiting SDP solvers dedicated to the solution of Kalman-Yakubovic-Popov semi-definite programs (KYP-SDPs). These SDPs inherit their name from…
Convolutional Neural Networks as 2-D systems
Dennis Gramlich, Patricia Pauli, Carsten W. Scherer +2
This paper introduces a novel representation of convolutional Neural Networks (CNNs) in terms of 2-D dynamical systems. To this end, the usual description of convolutional layers w…
Lipschitz constant estimation for 1D convolutional neural networks
Patricia Pauli, Dennis Gramlich, Frank Allgöwer
In this work, we propose a dissipativity-based method for Lipschitz constant estimation of 1D convolutional neural networks (CNNs). In particular, we analyze the dissipativity prop…
Fast identification and stabilization of unknown linear systems
Dennis Gramlich, Christian Ebenbauer
In the present work, a simple algorithm for stabilizing an unknown linear time-invariant system is proposed, assuming only that this system is stabilizable. The suggested algorithm…
Robust Differential Dynamic Programming
Dennis Gramlich, Carsten W. Scherer, Christian Ebenbauer
Differential Dynamic Programming is an optimal control technique often used for trajectory generation. Many variations of this algorithm have been developed in the literature, incl…
Neural network training under semidefinite constraints
Patricia Pauli, Niklas Funcke, Dennis Gramlich +2
This paper is concerned with the training of neural networks (NNs) under semidefinite constraints, which allows for NN training with robustness and stability guarantees. In particu…
Linear systems with neural network nonlinearities: Improved stability analysis via acausal Zames-Falb multipliers
Patricia Pauli, Dennis Gramlich, Julian Berberich +1
In this paper, we analyze the stability of feedback interconnections of a linear time-invariant system with a neural network nonlinearity in discrete time. Our analysis is based on…
Convex Synthesis of Accelerated Gradient Algorithms for Optimization and Saddle Point Problems using Lyapunov functions
Dennis Gramlich, Christian Ebenbauer, Carsten W. Scherer
This paper considers the problem of designing accelerated gradient-based algorithms for optimization and saddle-point problems. The class of objective functions is defined by a gen…